{"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/union-tensor-dict","entry":"union_tensor_dict","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":69,"n_papers_ran":61,"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":2,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":69,"n_places_pointer_only":10,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":1,"ran":0,"unverified":1},"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/protocol.py","file_url":"https://github.com/hexixiang/MT-SDPO/blob/HEAD/training/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"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/protocol.py","file_url":"https://github.com/AlibabaResearch/SignalCoverageRL/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"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/protocol.py","file_url":"https://github.com/QPHutu/golden_critic/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"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/protocol.py","file_url":"https://github.com/Moenupa/SDPO-CL/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2606.07705","paper":"/paper/arxiv-2606-07705","title":"SAW: Stage-Aware Dynamic Weighting for Multi-Objective Reinforcement Learning in Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Zhaolutuan/SAW","path":"verl/protocol.py","file_url":"https://github.com/Zhaolutuan/SAW/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"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/protocol.py","file_url":"https://github.com/lauyikfung/SDPG/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"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/protocol.py","file_url":"https://github.com/ZiqiZhao1/ROSD/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"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/protocol.py","file_url":"https://github.com/Lumina04/CARE/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"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/protocol.py","file_url":"https://github.com/Stellaris167/RAC/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"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/protocol.py","file_url":"https://github.com/horizon-llm/CTPO/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"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/protocol.py","file_url":"https://github.com/fairytale9/llm_bottleneck/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"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/protocol.py","file_url":"https://github.com/yuyongcan/DDRL/blob/HEAD/verl/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2604.18578","paper":"/paper/arxiv-2604-18578","title":"Bounded Ratio Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"bounded-ratio-rl/bounded_ratio_rl","path":"src/verl/protocol.py","file_url":"https://github.com/bounded-ratio-rl/bounded_ratio_rl/blob/HEAD/src/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"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/protocol.py","file_url":"https://github.com/lasgroup/SDPO/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"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/protocol.py","file_url":"https://github.com/ucsd-wang-lab-lm/tips/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"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/protocol.py","file_url":"https://github.com/shuohe1995/verl-kpo/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"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/protocol.py","file_url":"https://github.com/yining610/ctwa/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"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/protocol.py","file_url":"https://github.com/Easy195/FaithRL/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"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/protocol.py","file_url":"https://github.com/sail-sg/Stable-RL/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"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/protocol.py","file_url":"https://github.com/wenquanlu/PrAg-PO/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"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/protocol.py","file_url":"https://github.com/Within-yao/CoBA-RL/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2601.14896","paper":"/paper/arxiv-2601-14896","title":"Language-Coupled Reinforcement Learning for Multilingual Retrieval-Augmented Generation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Cherry-qwq/LcRL-Open","path":"verl/protocol.py","file_url":"https://github.com/Cherry-qwq/LcRL-Open/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2601.05167","paper":"/paper/arxiv-2601-05167","title":"RelayLLM: Efficient Reasoning via Collaborative Decoding","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Chengsong-Huang/RelayLLM","path":"RL_stage/verl/protocol.py","file_url":"https://github.com/Chengsong-Huang/RelayLLM/blob/HEAD/RL_stage/verl/protocol.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ad658a1d6fe829ba","mcp_get_code":{"code_sha256":"ad658a1d6fe829ba"}},{"arxiv_id":"2601.04767","paper":"/paper/arxiv-2601-04767","title":"AT 2 PO: Agentic Turn-based Policy Optimization via Tree Search","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"zzfoutofspace/ATPO","path":"ATPO/verl_atpo/verl/protocol.py","file_url":"https://github.com/zzfoutofspace/ATPO/blob/HEAD/ATPO/verl_atpo/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"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/protocol.py","file_url":"https://github.com/fatemi/verl/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2512.16848","paper":"/paper/arxiv-2512-16848","title":"Meta-RL Induces Exploration in Language Agents","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"mlbio-epfl/LaMer","path":"verl/protocol.py","file_url":"https://github.com/mlbio-epfl/LaMer/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2512.14157","paper":"/paper/arxiv-2512-14157","title":"Ophiuchus: Incentivizing Tool-augmented \"Think with Images\" for Joint Medical Segmentation, Understanding and Reasoning","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"SII-zyj/Ophiuchus","path":"verl/protocol.py","file_url":"https://github.com/SII-zyj/Ophiuchus/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2511.19900","paper":"/paper/arxiv-2511-19900","title":"Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"aiming-lab/Agent0","path":"Agent0-VL/verl/protocol.py","file_url":"https://github.com/aiming-lab/Agent0/blob/HEAD/Agent0-VL/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2510.14967","paper":"/paper/arxiv-2510-14967","title":"Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"GuoqingWang1/IGPO","path":"verl/protocol.py","file_url":"https://github.com/GuoqingWang1/IGPO/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2510.04678","paper":"/paper/arxiv-2510-04678","title":"Multi-Agent Tool-Integrated Policy Optimization","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"mzf666/MATPO","path":"verl/protocol.py","file_url":"https://github.com/mzf666/MATPO/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"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/protocol.py","file_url":"https://github.com/bytedance/EvoQuality/blob/HEAD/verl/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2507.07966","paper":"/paper/scaling-rl-to-long-videos","title":"Scaling RL to Long Videos","date":"2025-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NVlabs/Long-RL","path":"verl/protocol.py","file_url":"https://github.com/NVlabs/Long-RL/blob/HEAD/verl/protocol.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ad658a1d6fe829ba","mcp_get_code":{"code_sha256":"ad658a1d6fe829ba"}},{"arxiv_id":"2507.05386","paper":"/paper/reinforcement-fine-tuning-naturally-mitigates","title":"Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training","date":"2025-07-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhhvvv/rft_vs_sft","path":"EasyR1/verl/protocol.py","file_url":"https://github.com/zhhvvv/rft_vs_sft/blob/HEAD/EasyR1/verl/protocol.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ad658a1d6fe829ba","mcp_get_code":{"code_sha256":"ad658a1d6fe829ba"}},{"arxiv_id":"2506.12935","paper":"/paper/soundmind-rl-incentivized-logic-reasoning-for","title":"SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models","date":"2025-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xid32/SoundMind","path":"verl/protocol.py","file_url":"https://github.com/xid32/SoundMind/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2506.08672","paper":"/paper/rulereasoner-reinforced-rule-based-reasoning","title":"RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling","date":"2025-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bigai-nlco/rulereasoner","path":"verl/verl/protocol.py","file_url":"https://github.com/bigai-nlco/rulereasoner/blob/HEAD/verl/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2506.01908","paper":"/paper/reinforcement-learning-tuning-for-videollms","title":"Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency","date":"2025-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"appletea233/temporal-r1","path":"verl/protocol.py","file_url":"https://github.com/appletea233/temporal-r1/blob/HEAD/verl/protocol.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ad658a1d6fe829ba","mcp_get_code":{"code_sha256":"ad658a1d6fe829ba"}},{"arxiv_id":"2505.24875","paper":"/paper/reasongen-r1-cot-for-autoregressive-image","title":"ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL","date":"2025-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Franklin-Zhang0/ReasonGen-R1","path":"verl/protocol.py","file_url":"https://github.com/Franklin-Zhang0/ReasonGen-R1/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2505.22961","paper":"/paper/tomap-training-opponent-aware-llm-persuaders","title":"ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mind","date":"2025-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ulab-uiuc/ToMAP","path":"verl/protocol.py","file_url":"https://github.com/ulab-uiuc/ToMAP/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2505.20046","paper":"/paper/rearank-reasoning-re-ranking-agent-via","title":"REARANK: Reasoning Re-ranking Agent via Reinforcement Learning","date":"2025-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lezhang7/rearank","path":"verl/verl/protocol.py","file_url":"https://github.com/lezhang7/rearank/blob/HEAD/verl/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2505.18917","paper":"/paper/behavior-injection-preparing-language-models","title":"Behavior Injection: Preparing Language Models for Reinforcement Learning","date":"2025-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"czp16/bridge-llm-reasoning","path":"simple_verl/sverl/protocol.py","file_url":"https://github.com/czp16/bridge-llm-reasoning/blob/HEAD/simple_verl/sverl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2505.18822","paper":"/paper/adactrl-towards-adaptive-and-controllable","title":"AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting","date":"2025-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"joeying1019/adactrl","path":"verl/protocol.py","file_url":"https://github.com/joeying1019/adactrl/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2505.17063","paper":"/paper/synthetic-data-rl-task-definition-is-all-you","title":"Synthetic Data RL: Task Definition Is All You Need","date":"2025-05-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gydpku/data_synthesis_rl","path":"verl/protocol.py","file_url":"https://github.com/gydpku/data_synthesis_rl/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2505.16984","paper":"/paper/uft-unifying-supervised-and-reinforcement","title":"UFT: Unifying Supervised and Reinforcement Fine-Tuning","date":"2025-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liumy2010/uft","path":"verl/protocol.py","file_url":"https://github.com/liumy2010/uft/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2505.16282","paper":"/paper/arpo-end-to-end-policy-optimization-for-gui","title":"ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay","date":"2025-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dvlab-research/arpo","path":"verl/protocol.py","file_url":"https://github.com/dvlab-research/arpo/blob/HEAD/verl/protocol.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ad658a1d6fe829ba","mcp_get_code":{"code_sha256":"ad658a1d6fe829ba"}},{"arxiv_id":"2505.14362","paper":"/paper/deepeyes-incentivizing-thinking-with-images","title":"DeepEyes: Incentivizing \"Thinking with Images\" via Reinforcement Learning","date":"2025-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"visual-agent/deepeyes","path":"verl/protocol.py","file_url":"https://github.com/visual-agent/deepeyes/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2505.14146","paper":"/paper/s3-you-don-t-need-that-much-data-to-train-a","title":"s3: You Don't Need That Much Data to Train a Search Agent via RL","date":"2025-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pat-jj/s3","path":"s3/llm_agent/generation_s3.py","file_url":"https://github.com/pat-jj/s3/blob/HEAD/s3/llm_agent/generation_s3.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2505.13379","paper":"/paper/thinkless-llm-learns-when-to-think","title":"Thinkless: LLM Learns When to Think","date":"2025-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vainf/thinkless","path":"verl/verl/protocol.py","file_url":"https://github.com/vainf/thinkless/blob/HEAD/verl/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2505.12929","paper":"/paper/do-not-let-low-probability-tokens-over","title":"Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs","date":"2025-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhyang2226/ar-lopti","path":"verl/protocol.py","file_url":"https://github.com/zhyang2226/ar-lopti/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2505.11049","paper":"/paper/2505-11049","title":"GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning","date":"2025-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yueliu1999/guardreasoner-vl","path":"train/EasyR1/verl/protocol.py","file_url":"https://github.com/yueliu1999/guardreasoner-vl/blob/HEAD/train/EasyR1/verl/protocol.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ad658a1d6fe829ba","mcp_get_code":{"code_sha256":"ad658a1d6fe829ba"}},{"arxiv_id":"2505.05315","paper":"/paper/scalable-chain-of-thoughts-via-elastic","title":"Scalable Chain of Thoughts via Elastic Reasoning","date":"2025-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforceairesearch/elastic-reasoning","path":"verl/verl/protocol.py","file_url":"https://github.com/salesforceairesearch/elastic-reasoning/blob/HEAD/verl/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2505.04588","paper":"/paper/zerosearch-incentivize-the-search-capability","title":"ZeroSearch: Incentivize the Search Capability of LLMs without Searching","date":"2025-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alibaba-nlp/zerosearch","path":"verl/protocol.py","file_url":"https://github.com/alibaba-nlp/zerosearch/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2504.20571","paper":"/paper/reinforcement-learning-for-reasoning-in-large","title":"Reinforcement Learning for Reasoning in Large Language Models with One Training Example","date":"2025-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ypwang61/one-shot-rlvr","path":"verl/protocol.py","file_url":"https://github.com/ypwang61/one-shot-rlvr/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2504.08600","paper":"/paper/sql-r1-training-natural-language-to-sql","title":"SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2025-04","title_source":"archive","repo":"IDEA-FinAI/SQL-R1","path":"verl/protocol.py","file_url":"https://github.com/IDEA-FinAI/SQL-R1/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2504.05520","paper":"/paper/efficient-reinforcement-finetuning-via","title":"Efficient Reinforcement Finetuning via Adaptive Curriculum Learning","date":"2025-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uscnlp-lime/verl","path":"verl/protocol.py","file_url":"https://github.com/uscnlp-lime/verl/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2504.01698","paper":"/paper/tom-rl-reinforcement-learning-unlocks-theory","title":"Do Theory of Mind Benchmarks Need Explicit Human-like Reasoning in Language Models?","date":"2025-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bigai-ai/ToM-RL","path":"verl/protocol.py","file_url":"https://github.com/bigai-ai/ToM-RL/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2504.01296","paper":"/paper/thinkprune-pruning-long-chain-of-thought-of","title":"ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning","date":"2025-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"UCSB-NLP-Chang/ThinkPrune","path":"verl/protocol.py","file_url":"https://github.com/UCSB-NLP-Chang/ThinkPrune/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2503.22342","paper":"/paper/cppo-accelerating-the-training-of-group","title":"CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models","date":"2025-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lzhxmu/cppo","path":"cppo_verl/verl/protocol.py","file_url":"https://github.com/lzhxmu/cppo/blob/HEAD/cppo_verl/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2503.17352","paper":"/paper/openvlthinker-an-early-exploration-to-complex","title":"OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement","date":"2025-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yihedeng9/openvlthinker","path":"EasyR1/verl/protocol.py","file_url":"https://github.com/yihedeng9/openvlthinker/blob/HEAD/EasyR1/verl/protocol.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ad658a1d6fe829ba","mcp_get_code":{"code_sha256":"ad658a1d6fe829ba"}},{"arxiv_id":"2503.10460","paper":"/paper/light-r1-curriculum-sft-dpo-and-rl-for-long","title":"Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond","date":"2025-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Qihoo360/Light-R1","path":"deepscaler-release/verl/verl/protocol.py","file_url":"https://github.com/Qihoo360/Light-R1/blob/HEAD/deepscaler-release/verl/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2503.06580","paper":"/paper/agent-models-internalizing-chain-of-action","title":"Agent models: Internalizing Chain-of-Action Generation into Reasoning models","date":"2025-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adam-bjtu/autocoa","path":"RL_training/verl/protocol.py","file_url":"https://github.com/adam-bjtu/autocoa/blob/HEAD/RL_training/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2502.19613","paper":"/paper/self-rewarding-correction-for-mathematical","title":"Self-rewarding correction for mathematical reasoning","date":"2025-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"agentica-project/verl-pipeline","path":"verl/protocol.py","file_url":"https://github.com/agentica-project/verl-pipeline/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2502.14768","paper":"/paper/logic-rl-unleashing-llm-reasoning-with-rule","title":"Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning","date":"2025-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Unakar/Logic-RL","path":"verl/protocol.py","file_url":"https://github.com/Unakar/Logic-RL/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2410.21236","paper":"/paper/flaming-hot-initiation-with-regular-execution","title":"Flaming-hot Initiation with Regular Execution Sampling for Large Language Models","date":"2024-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yaof20/real","path":"verl/protocol.py","file_url":"https://github.com/yaof20/real/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2409.19256","paper":"/paper/hybridflow-a-flexible-and-efficient-rlhf","title":"HybridFlow: A Flexible and Efficient RLHF Framework","date":"2024-09-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"du-nlp-lab/lengthreward","path":"verl/protocol.py","file_url":"https://github.com/du-nlp-lab/lengthreward/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"openreview_dzcDbh8ewp","paper":null,"title":"arXiv:openreview_dzcDbh8ewp","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Xiao-Youth/LECTOR","path":"verl/protocol.py","file_url":"https://github.com/Xiao-Youth/LECTOR/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"openreview_Y1rHxA58If","paper":null,"title":"arXiv:openreview_Y1rHxA58If","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"qiancheng0/ToolRL","path":"verl/protocol.py","file_url":"https://github.com/qiancheng0/ToolRL/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"openreview_Y1PXB8HBV7","paper":null,"title":"arXiv:openreview_Y1PXB8HBV7","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"youwyouw/mirl-main","path":"verl/protocol.py","file_url":"https://github.com/youwyouw/mirl-main/blob/HEAD/verl/protocol.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ad658a1d6fe829ba","mcp_get_code":{"code_sha256":"ad658a1d6fe829ba"}},{"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/protocol.py","file_url":"https://github.com/ShadeCloak/IP-GRM/blob/HEAD/verl/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"arxiv_id":"2025.findings-emnlp.1015","paper":null,"title":"arXiv:2025.findings-emnlp.1015","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"fzp0424/MT-R1-Zero","path":"verl/protocol.py","file_url":"https://github.com/fzp0424/MT-R1-Zero/blob/HEAD/verl/protocol.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21331a58f93375e4","mcp_get_code":{"code_sha256":"21331a58f93375e4"}}]}