{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/generate-config-from-args","entry":"generate_config_from_args","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":68,"n_papers_ran":68,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":3,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":68,"n_places_pointer_only":21,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":3,"unverified":0},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2609.02548","paper":"/paper/arxiv-2609-02548","title":"Learn from Whoever Is Right: Answer-Verified Multi-Teacher Distillation for Multi-Domain LLMs","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"hexixiang/MT-SDPO","path":"training/verl/model_merger/base_model_merger.py","file_url":"https://github.com/hexixiang/MT-SDPO/blob/HEAD/training/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2609.01245","paper":"/paper/arxiv-2609-01245","title":"Explore More, Drift Less: Outcome-Only Reinforcement Learning Can Suffice for Long-Horizon Interactive Agents","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"AlibabaResearch/SignalCoverageRL","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/AlibabaResearch/SignalCoverageRL/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2608.24696","paper":"/paper/arxiv-2608-24696","title":"On-policy Distillation with Verifiable Reward","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"LeapLabTHU/OPDVR","path":"verl/verl/model_merger/base_model_merger.py","file_url":"https://github.com/LeapLabTHU/OPDVR/blob/HEAD/verl/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2608.24350","paper":"/paper/arxiv-2608-24350","title":"FARCA: Fact-Aligned Reliability-Aware Credit Assignment for Reinforcement Learning with Factual Supervision","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"verl-project/verl","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/verl-project/verl/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"45205d24c28c95d4","mcp_get_code":{"code_sha256":"45205d24c28c95d4"}},{"arxiv_id":"2608.23566","paper":"/paper/arxiv-2608-23566","title":"Best Practice Critic Optimization BEST PRACTICE CRITIC OPTIMIZATION","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"QPHutu/golden_critic","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/QPHutu/golden_critic/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"45205d24c28c95d4","mcp_get_code":{"code_sha256":"45205d24c28c95d4"}},{"arxiv_id":"2608.19181","paper":"/paper/arxiv-2608-19181","title":"Beyond Teacher Likelihood: Group-Calibrated On-Policy Distillation for Long-Context Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"SolereZhang/GC-OPD","path":"verl/verl/model_merger/base_model_merger.py","file_url":"https://github.com/SolereZhang/GC-OPD/blob/HEAD/verl/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2608.14728","paper":"/paper/arxiv-2608-14728","title":"TAIL-AWARE TOP-k ON-POLICY DISTILLATION","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"HuipengHuang/TA-OPD","path":"verl/verl/model_merger/base_model_merger.py","file_url":"https://github.com/HuipengHuang/TA-OPD/blob/HEAD/verl/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"45205d24c28c95d4","mcp_get_code":{"code_sha256":"45205d24c28c95d4"}},{"arxiv_id":"2608.02139","paper":"/paper/arxiv-2608-02139","title":"Self-Improving Large Language Models via Progressive Experience Evolution","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"rrrsj/SPEE","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/rrrsj/SPEE/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2608.01743","paper":"/paper/arxiv-2608-01743","title":"Toward Plasticity-Preserving KL Regularization for Capability Retention in LLM Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"Lumina04/CoKL","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/Lumina04/CoKL/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2607.19395","paper":"/paper/arxiv-2607-19395","title":"From Trajectories to Prefixes: Reusing Teacher Trajectories via Replayed Prefixes and Online Continuation","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"HappynessI/Prefix_GRPO","path":"verl/verl/model_merger/base_model_merger.py","file_url":"https://github.com/HappynessI/Prefix_GRPO/blob/HEAD/verl/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2607.13124","paper":"/paper/arxiv-2607-13124","title":"ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"VisionOPD/Vision-OPD","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/VisionOPD/Vision-OPD/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2607.10481","paper":"/paper/arxiv-2607-10481","title":"ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"Hesse73/ARMOR","path":"verl/verl/model_merger/base_model_merger.py","file_url":"https://github.com/Hesse73/ARMOR/blob/HEAD/verl/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2607.07976","paper":"/paper/arxiv-2607-07976","title":"When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"xiuyilou/TACO","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/xiuyilou/TACO/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2607.01763","paper":"/paper/arxiv-2607-01763","title":"DENSER ̸ = BETTER: LIMITS OF ON-POLICY SELF-DISTILLATION FOR CONTINUAL POST-TRAINING","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"Moenupa/SDPO-CL","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/Moenupa/SDPO-CL/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2606.25757","paper":"/paper/arxiv-2606-25757","title":"OPERA: Aligning Open-Ended Reasoning via Objective Perplexity-based Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"pangpang-xuan/OPERA","path":"verl/verl/model_merger/base_model_merger.py","file_url":"https://github.com/pangpang-xuan/OPERA/blob/HEAD/verl/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9c496dae615ba2a8","mcp_get_code":{"code_sha256":"9c496dae615ba2a8"}},{"arxiv_id":"2606.24994","paper":"/paper/arxiv-2606-24994","title":"ExTra: Exploratory Trajectory Optimization for Language Model Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"allen4747/extra","path":"verl/verl/model_merger/base_model_merger.py","file_url":"https://github.com/allen4747/extra/blob/HEAD/verl/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2606.20008","paper":"/paper/arxiv-2606-20008","title":"VIMPO: Value-Implicit Policy Optimization for LLMs","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"backprop07/VIMPO","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/backprop07/VIMPO/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2606.18967","paper":"/paper/arxiv-2606-18967","title":"EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"furiosa-ai/EfficientRollout","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/furiosa-ai/EfficientRollout/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2606.09091","paper":"/paper/arxiv-2606-09091","title":"Stabilizing On-Policy Distillation for MLLM Reasoning with Global Normalization","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"OPPO-Mente-Lab/GNDPO","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/OPPO-Mente-Lab/GNDPO/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9c496dae615ba2a8","mcp_get_code":{"code_sha256":"9c496dae615ba2a8"}},{"arxiv_id":"2606.09052","paper":"/paper/arxiv-2606-09052","title":"INFUSER: Influence-Guided Self-Evolution Improves Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"FFishy-git/INFUSER","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/FFishy-git/INFUSER/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2606.06021","paper":"/paper/arxiv-2606-06021","title":"OPRD: On-Policy Representation Distillation","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"ShenzhiYang2000/OPRD","path":"verl/verl/model_merger/base_model_merger.py","file_url":"https://github.com/ShenzhiYang2000/OPRD/blob/HEAD/verl/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2606.04036","paper":"/paper/arxiv-2606-04036","title":"Self-Distilled Policy Gradient","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"lauyikfung/SDPG","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/lauyikfung/SDPG/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2606.02684","paper":"/paper/arxiv-2606-02684","title":"Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"YuYingLi0/FiRe-OPD","path":"verl/verl/model_merger/base_model_merger.py","file_url":"https://github.com/YuYingLi0/FiRe-OPD/blob/HEAD/verl/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2606.00593","paper":"/paper/arxiv-2606-00593","title":"SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"KhanCold/spader","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/KhanCold/spader/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2605.28014","paper":"/paper/arxiv-2605-28014","title":"ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"ZiqiZhao1/ROSD","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/ZiqiZhao1/ROSD/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2605.27865","paper":"/paper/arxiv-2605-27865","title":"MERIT: Matching Expertise via Rubric-Informed Training for Reviewer Assignment","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Luli3220/MERIT","path":"MERIT-Assessor/verl/model_merger/base_model_merger.py","file_url":"https://github.com/Luli3220/MERIT/blob/HEAD/MERIT-Assessor/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2605.25920","paper":"/paper/arxiv-2605-25920","title":"Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"AlexFanw/LegalSearch-R1","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/AlexFanw/LegalSearch-R1/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2605.25864","paper":"/paper/arxiv-2605-25864","title":"When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Lumina04/CARE","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/Lumina04/CARE/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9c496dae615ba2a8","mcp_get_code":{"code_sha256":"9c496dae615ba2a8"}},{"arxiv_id":"2605.25198","paper":"/paper/arxiv-2605-25198","title":"Hide to Guide: Learning via Semantic Masking","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"mit-han-lab/SMEPO","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/mit-han-lab/SMEPO/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2605.16999","paper":"/paper/arxiv-2605-16999","title":"Ranking-Aware Calibration for Reliable Multimodal Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Stellaris167/RAC","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/Stellaris167/RAC/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2605.11739","paper":"/paper/arxiv-2605-11739","title":"Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"caiyuchen-ustc/EffOPD","path":"EffOPD/verl/verl/model_merger/base_model_merger.py","file_url":"https://github.com/caiyuchen-ustc/EffOPD/blob/HEAD/EffOPD/verl/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2605.07331","paper":"/paper/arxiv-2605-07331","title":"Rethinking Importance Sampling in LLM Policy Optimization: A Cumulative Token Perspective","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"horizon-llm/CTPO","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/horizon-llm/CTPO/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2605.01111","paper":"/paper/arxiv-2605-01111","title":"When Less is Enough: Efficient Inference via Collaborative Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"fairytale9/llm_bottleneck","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/fairytale9/llm_bottleneck/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2604.25444","paper":"/paper/arxiv-2604-25444","title":"One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinement","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"newera-xiao/ReQueR","path":"verl/verl/model_merger/base_model_merger.py","file_url":"https://github.com/newera-xiao/ReQueR/blob/HEAD/verl/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2604.21327","paper":"/paper/arxiv-2604-21327","title":"Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"yuyongcan/DDRL","path":"verl/verl/model_merger/base_model_merger.py","file_url":"https://github.com/yuyongcan/DDRL/blob/HEAD/verl/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9c496dae615ba2a8","mcp_get_code":{"code_sha256":"9c496dae615ba2a8"}},{"arxiv_id":"2604.17928","paper":"/paper/arxiv-2604-17928","title":"HEALing Entropy Collapse: Enhancing Exploration in Few-Shot RLVR via Hybrid-Domain Entropy Dynamics Alignment","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"XMUDeepLIT/HEAL","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/XMUDeepLIT/HEAL/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9c496dae615ba2a8","mcp_get_code":{"code_sha256":"9c496dae615ba2a8"}},{"arxiv_id":"2604.05818","paper":"/paper/arxiv-2604-05818","title":"WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"zhuyjan/WikiSeeker","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/zhuyjan/WikiSeeker/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2604.00698","paper":"/paper/arxiv-2604-00698","title":"Learning to Hint for Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"Andree-9/HiLL","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/Andree-9/HiLL/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2603.24472","paper":"/paper/arxiv-2603-24472","title":"Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"lasgroup/SDPO","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/lasgroup/SDPO/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2603.22293","paper":"/paper/arxiv-2603-22293","title":"TIPS: Turn-Level Information-Potential Reward Shaping for Search-Augmented LLMs","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"ucsd-wang-lab-lm/tips","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/ucsd-wang-lab-lm/tips/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2603.20046","paper":"/paper/arxiv-2603-20046","title":"Experience is the Best Teacher: Motivating Effective Exploration in Reinforcement Learning for LLMs","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"sikelifei/HeRL","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/sikelifei/HeRL/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2603.19880","paper":"/paper/arxiv-2603-19880","title":"What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"Jasper-Yan/SCRL","path":"verl/verl/model_merger/base_model_merger.py","file_url":"https://github.com/Jasper-Yan/SCRL/blob/HEAD/verl/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9c496dae615ba2a8","mcp_get_code":{"code_sha256":"9c496dae615ba2a8"}},{"arxiv_id":"2603.16654","paper":"/paper/arxiv-2603-16654","title":"Omanic: Towards Step-wise Evaluation of Multi-hop Reasoning in Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"XiaojieGu/Omanic","path":"verl/verl/model_merger/base_model_merger.py","file_url":"https://github.com/XiaojieGu/Omanic/blob/HEAD/verl/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2603.12109","paper":"/paper/arxiv-2603-12109","title":"On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"unimpor/T3","path":"verl/verl/model_merger/base_model_merger.py","file_url":"https://github.com/unimpor/T3/blob/HEAD/verl/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2603.10101","paper":"/paper/arxiv-2603-10101","title":"CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"Qwen-Applications/CLIPO","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/Qwen-Applications/CLIPO/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2603.07079","paper":"/paper/arxiv-2603-07079","title":"Entropy-Aware On-Policy Distillation of Language Models","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"WLS04/EOPD","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/WLS04/EOPD/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2602.17550","paper":"/paper/arxiv-2602-17550","title":"MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"FlyTune/MASPO-RL","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/FlyTune/MASPO-RL/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2602.10693","paper":"/paper/arxiv-2602-10693","title":"VESPO: Variational Sequence-level Soft Policy Optimization for Off-Policy LLM Training","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"FloyedShen/VESPO","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/FloyedShen/VESPO/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2602.10609","paper":"/paper/arxiv-2602-10609","title":"Online Causal Kalman Filtering for Stable and Effective Policy Optimization","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"shuohe1995/verl-kpo","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/shuohe1995/verl-kpo/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2602.06869","paper":"/paper/arxiv-2602-06869","title":"Uncovering Cross-Objective Interference in Multi-Objective Alignment","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"yining610/ctwa","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/yining610/ctwa/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2602.05897","paper":"/paper/arxiv-2602-05897","title":"Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning Models","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Easy195/FaithRL","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/Easy195/FaithRL/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2602.04879","paper":"/paper/arxiv-2602-04879","title":"Rethinking the Trust Region in LLM Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"sail-sg/Stable-RL","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/sail-sg/Stable-RL/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2602.03190","paper":"/paper/arxiv-2602-03190","title":"PrAg-PO: Prompt Augmented Policy Optimization for Robust and Diverse Mathematical Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"wenquanlu/PrAg-PO","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/wenquanlu/PrAg-PO/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2602.03143","paper":"/paper/arxiv-2602-03143","title":"Self-Hinting Language Models Enhance Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"BaohaoLiao/SAGE","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/BaohaoLiao/SAGE/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2602.03048","paper":"/paper/arxiv-2602-03048","title":"CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Within-yao/CoBA-RL","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/Within-yao/CoBA-RL/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2602.02518","paper":"/paper/arxiv-2602-02518","title":"GRAPHDANCER: Training LLMs to Explore and Reason over Graphs via Two-Stage Curriculum Post-Training","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"leopoldwhite/GraphDancer","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/leopoldwhite/GraphDancer/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2601.22648","paper":"/paper/arxiv-2601-22648","title":"UCPO: Uncertainty-Aware Policy Optimization","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"xzhouzeng/ucpo","path":"train/verl/model_merger/base_model_merger.py","file_url":"https://github.com/xzhouzeng/ucpo/blob/HEAD/train/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2601.17687","paper":"/paper/arxiv-2601-17687","title":"Agentic reinforcement learning empowers next-generation chemical language models for molecular design and synthesis","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"HowardLi1984/ChemCraft","path":"chemcraft_rl/verl/model_merger/base_model_merger.py","file_url":"https://github.com/HowardLi1984/ChemCraft/blob/HEAD/chemcraft_rl/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2601.05508","paper":"/paper/arxiv-2601-05508","title":"Enabling Stroke-Level Structural Analysis of Hieroglyphic Scripts without Language-Specific Priors","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"THUNLP-MT/HieroSA","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/THUNLP-MT/HieroSA/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2601.04537","paper":"/paper/arxiv-2601-04537","title":"Linear Dynamics in the RLVR Training of Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Miaow-Lab/RLVR-Linearity","path":"verl/verl/model_merger/base_model_merger.py","file_url":"https://github.com/Miaow-Lab/RLVR-Linearity/blob/HEAD/verl/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2601.02648","paper":"/paper/arxiv-2601-02648","title":"Prioritized Replay for RL Post-training","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"fatemi/verl","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/fatemi/verl/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2510.08630","paper":"/paper/arxiv-2510-08630","title":"ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"JingbiaoMei/ExPO-HM","path":"verl/verl/model_merger/base_model_merger.py","file_url":"https://github.com/JingbiaoMei/ExPO-HM/blob/HEAD/verl/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2509.25787","paper":"/paper/arxiv-2509-25787","title":"Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"bytedance/EvoQuality","path":"verl/verl/model_merger/base_model_merger.py","file_url":"https://github.com/bytedance/EvoQuality/blob/HEAD/verl/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"2504.16084","paper":"/paper/ttrl-test-time-reinforcement-learning","title":"TTRL: Test-Time Reinforcement Learning","date":"2025-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"prime-rl/ttrl","path":"verl/verl/model_merger/base_model_merger.py","file_url":"https://github.com/prime-rl/ttrl/blob/HEAD/verl/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9c496dae615ba2a8","mcp_get_code":{"code_sha256":"9c496dae615ba2a8"}},{"arxiv_id":"2410.02992","paper":"/paper/guided-stream-of-search-learning-to-better","title":"Guided Stream of Search: Learning to Better Search with Language Models via Optimal Path Guidance","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"snu-mllab/guided-rest","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/snu-mllab/guided-rest/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"openreview_v70fTOqer2","paper":null,"title":"arXiv:openreview_v70fTOqer2","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"liziniu/KnapsackRL","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/liziniu/KnapsackRL/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"openreview_lbaBsu0CaY","paper":null,"title":"arXiv:openreview_lbaBsu0CaY","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Tunanzzz/Meerkat-VL","path":"verl/model_merger/base_model_merger.py","file_url":"https://github.com/Tunanzzz/Meerkat-VL/blob/HEAD/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}},{"arxiv_id":"openreview_VZDlkXuIQc","paper":null,"title":"arXiv:openreview_VZDlkXuIQc","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"ShadeCloak/IP-GRM","path":"verl/verl/model_merger/base_model_merger.py","file_url":"https://github.com/ShadeCloak/IP-GRM/blob/HEAD/verl/verl/model_merger/base_model_merger.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8896f4e2bafe8abc","mcp_get_code":{"code_sha256":"8896f4e2bafe8abc"}}]}