{"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/is-ipv4","entry":"is_ipv4","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":42,"n_papers_ran":42,"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":1,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":42,"n_places_pointer_only":10,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"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/utils/net_utils.py","file_url":"https://github.com/hexixiang/MT-SDPO/blob/HEAD/training/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/AlibabaResearch/SignalCoverageRL/blob/HEAD/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/verl-project/verl/blob/HEAD/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/QPHutu/golden_critic/blob/HEAD/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/rrrsj/SPEE/blob/HEAD/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/xiuyilou/TACO/blob/HEAD/verl/utils/net_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/Moenupa/SDPO-CL/blob/HEAD/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/OPPO-Mente-Lab/GNDPO/blob/HEAD/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/FFishy-git/INFUSER/blob/HEAD/verl/utils/net_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"arxiv_id":"2606.05793","paper":"/paper/arxiv-2606-05793","title":"CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"langfengQ/verl-agent","path":"verl/utils/net_utils.py","file_url":"https://github.com/langfengQ/verl-agent/blob/HEAD/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/lauyikfung/SDPG/blob/HEAD/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/ZiqiZhao1/ROSD/blob/HEAD/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/Luli3220/MERIT/blob/HEAD/MERIT-Assessor/verl/utils/net_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/AlexFanw/LegalSearch-R1/blob/HEAD/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/Lumina04/CARE/blob/HEAD/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/mit-han-lab/SMEPO/blob/HEAD/verl/utils/net_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/Stellaris167/RAC/blob/HEAD/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/horizon-llm/CTPO/blob/HEAD/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/yuyongcan/DDRL/blob/HEAD/verl/verl/utils/net_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/lasgroup/SDPO/blob/HEAD/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/ucsd-wang-lab-lm/tips/blob/HEAD/verl/utils/net_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"arxiv_id":"2603.10624","paper":"/paper/arxiv-2603-10624","title":"Reinforcement Learning with Conditional Expectation Reward","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"changyi7231/CER","path":"verl/utils/net_utils.py","file_url":"https://github.com/changyi7231/CER/blob/HEAD/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/Qwen-Applications/CLIPO/blob/HEAD/verl/utils/net_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"arxiv_id":"2602.12113","paper":"/paper/arxiv-2602-12113","title":"Adaptive Reflection and Length Coordinated Penalty (ARLCP) STOP UNNECESSARY REFLECTION: TRAINING LRMS FOR EFFICIENT REASONING WITH ADAPTIVE REFLEC-TION AND LENGTH COORDINATED PENALTY","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"ZeweiYu1/ARLCP","path":"verl/utils/net_utils.py","file_url":"https://github.com/ZeweiYu1/ARLCP/blob/HEAD/verl/utils/net_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"arxiv_id":"2602.11909","paper":"/paper/arxiv-2602-11909","title":"Echo: Towards Advanced Audio Comprehension via Audio-Interleaved Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"wdqqdw/Echo","path":"verl/verl/utils/net_utils.py","file_url":"https://github.com/wdqqdw/Echo/blob/HEAD/verl/verl/utils/net_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/shuohe1995/verl-kpo/blob/HEAD/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/yining610/ctwa/blob/HEAD/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/Easy195/FaithRL/blob/HEAD/verl/utils/net_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/sail-sg/Stable-RL/blob/HEAD/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/Within-yao/CoBA-RL/blob/HEAD/verl/utils/net_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"arxiv_id":"2601.04786","paper":"/paper/arxiv-2601-04786","title":"AgentOCR: Reimagining Agent History via Optical Self-Compression","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"langfengQ/AgentOCR","path":"verl/utils/net_utils.py","file_url":"https://github.com/langfengQ/AgentOCR/blob/HEAD/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/zzfoutofspace/ATPO/blob/HEAD/ATPO/verl_atpo/verl/utils/net_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/fatemi/verl/blob/HEAD/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/mlbio-epfl/LaMer/blob/HEAD/verl/utils/net_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/SII-zyj/Ophiuchus/blob/HEAD/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/GuoqingWang1/IGPO/blob/HEAD/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/mzf666/MATPO/blob/HEAD/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/xid32/SoundMind/blob/HEAD/verl/utils/net_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/bigai-nlco/rulereasoner/blob/HEAD/verl/verl/utils/net_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/du-nlp-lab/lengthreward/blob/HEAD/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/Xiao-Youth/LECTOR/blob/HEAD/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"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/utils/net_utils.py","file_url":"https://github.com/ShadeCloak/IP-GRM/blob/HEAD/verl/verl/utils/net_utils.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":"735e93af30b15fa9","mcp_get_code":{"code_sha256":"735e93af30b15fa9"}}]}