{"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/reward-func","entry":"reward_func","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":49,"n_papers_ran":46,"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":6,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":49,"n_places_pointer_only":16,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":1,"ran":1,"unverified":3},"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":"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/recipe/r1/reward_score.py","file_url":"https://github.com/LeapLabTHU/OPDVR/blob/HEAD/verl/recipe/r1/reward_score.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":"8a84f8cc921357e2","mcp_get_code":{"code_sha256":"8a84f8cc921357e2"}},{"arxiv_id":"2608.09836","paper":"/paper/arxiv-2608-09836","title":"Mismatch Matters: On-Policy Distillation Beyond Token Agreement","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"yzc-666/TIDE","path":"verl/recipe/r1/reward_score.py","file_url":"https://github.com/yzc-666/TIDE/blob/HEAD/verl/recipe/r1/reward_score.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":"8a84f8cc921357e2","mcp_get_code":{"code_sha256":"8a84f8cc921357e2"}},{"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":"recipe/r1/reward_score.py","file_url":"https://github.com/Lumina04/CoKL/blob/HEAD/recipe/r1/reward_score.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":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"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/recipe/r1/reward_score.py","file_url":"https://github.com/Hesse73/ARMOR/blob/HEAD/verl/recipe/r1/reward_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"arxiv_id":"2606.26790","paper":"/paper/arxiv-2606-26790","title":"OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"jinyangwu/OPID","path":"recipe/r1/reward_score.py","file_url":"https://github.com/jinyangwu/OPID/blob/HEAD/recipe/r1/reward_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"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/recipe/r1/reward_score.py","file_url":"https://github.com/pangpang-xuan/OPERA/blob/HEAD/verl/recipe/r1/reward_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"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/recipe/r1/reward_score.py","file_url":"https://github.com/allen4747/extra/blob/HEAD/verl/recipe/r1/reward_score.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":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"arxiv_id":"2606.19236","paper":"/paper/arxiv-2606-19236","title":"STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"hp-luo/STARE","path":"recipe/r1/reward_score.py","file_url":"https://github.com/hp-luo/STARE/blob/HEAD/recipe/r1/reward_score.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":"8a84f8cc921357e2","mcp_get_code":{"code_sha256":"8a84f8cc921357e2"}},{"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/recipe/r1/reward_score.py","file_url":"https://github.com/ShenzhiYang2000/OPRD/blob/HEAD/verl/recipe/r1/reward_score.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":"8a84f8cc921357e2","mcp_get_code":{"code_sha256":"8a84f8cc921357e2"}},{"arxiv_id":"2606.04923","paper":"/paper/arxiv-2606-04923","title":"Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"THUAIS-Lab/CHERRL","path":"recipe/r1/reward_score.py","file_url":"https://github.com/THUAIS-Lab/CHERRL/blob/HEAD/recipe/r1/reward_score.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":"8a84f8cc921357e2","mcp_get_code":{"code_sha256":"8a84f8cc921357e2"}},{"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/recipe/r1/reward_score.py","file_url":"https://github.com/YuYingLi0/FiRe-OPD/blob/HEAD/verl/recipe/r1/reward_score.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":"8a84f8cc921357e2","mcp_get_code":{"code_sha256":"8a84f8cc921357e2"}},{"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":"recipe/r1/reward_score.py","file_url":"https://github.com/Lumina04/CARE/blob/HEAD/recipe/r1/reward_score.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":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"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/recipe/r1/reward_score.py","file_url":"https://github.com/caiyuchen-ustc/EffOPD/blob/HEAD/EffOPD/verl/recipe/r1/reward_score.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":"8a84f8cc921357e2","mcp_get_code":{"code_sha256":"8a84f8cc921357e2"}},{"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":"recipe/r1/reward_score.py","file_url":"https://github.com/fairytale9/llm_bottleneck/blob/HEAD/recipe/r1/reward_score.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":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"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":"recipe/r1/reward_score.py","file_url":"https://github.com/XMUDeepLIT/HEAL/blob/HEAD/recipe/r1/reward_score.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":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"arxiv_id":"2604.17555","paper":"/paper/arxiv-2604-17555","title":"CoSearch: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Search","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"snap-research/CoSearch","path":"verl/recipe/r1/reward_score.py","file_url":"https://github.com/snap-research/CoSearch/blob/HEAD/verl/recipe/r1/reward_score.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":"8a84f8cc921357e2","mcp_get_code":{"code_sha256":"8a84f8cc921357e2"}},{"arxiv_id":"2604.17252","paper":"/paper/arxiv-2604-17252","title":"Seeing Isn't Believing: Mitigating Belief Inertia via Active Intervention in Embodied Agents","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"WangHanLinHenry/EVU","path":"verl-agent/recipe/r1/reward_score.py","file_url":"https://github.com/WangHanLinHenry/EVU/blob/HEAD/verl-agent/recipe/r1/reward_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"arxiv_id":"2604.09793","paper":"/paper/arxiv-2604-09793","title":"GIANTS: Generative Insight Anticipation from Scientific Literature","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"joyheyueya/giants","path":"recipe/r1/reward_score.py","file_url":"https://github.com/joyheyueya/giants/blob/HEAD/recipe/r1/reward_score.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":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"arxiv_id":"2604.03993","paper":"/paper/arxiv-2604-03993","title":"Can LLMs Learn to Reason Robustly under Noisy Supervision?","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"ShenzhiYang2000/OLR","path":"recipe/r1/reward_score.py","file_url":"https://github.com/ShenzhiYang2000/OLR/blob/HEAD/recipe/r1/reward_score.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":"8a84f8cc921357e2","mcp_get_code":{"code_sha256":"8a84f8cc921357e2"}},{"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":"recipe/r1/reward_score.py","file_url":"https://github.com/sikelifei/HeRL/blob/HEAD/recipe/r1/reward_score.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":"8a84f8cc921357e2","mcp_get_code":{"code_sha256":"8a84f8cc921357e2"}},{"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/recipe/r1/reward_score.py","file_url":"https://github.com/Jasper-Yan/SCRL/blob/HEAD/verl/recipe/r1/reward_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"arxiv_id":"2603.17145","paper":"/paper/arxiv-2603-17145","title":"REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"YasminZhang/REAL","path":"recipe/r1/reward_score.py","file_url":"https://github.com/YasminZhang/REAL/blob/HEAD/recipe/r1/reward_score.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":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"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/recipe/r1/reward_score.py","file_url":"https://github.com/unimpor/T3/blob/HEAD/verl/recipe/r1/reward_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"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":"recipe/r1/reward_score.py","file_url":"https://github.com/WLS04/EOPD/blob/HEAD/recipe/r1/reward_score.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":"8a84f8cc921357e2","mcp_get_code":{"code_sha256":"8a84f8cc921357e2"}},{"arxiv_id":"2603.04597","paper":"/paper/arxiv-2603-04597","title":"Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"LuckyyySTA/GOLF","path":"golf/verl/recipe/r1/reward_score.py","file_url":"https://github.com/LuckyyySTA/GOLF/blob/HEAD/golf/verl/recipe/r1/reward_score.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":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"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":"recipe/r1/reward_score.py","file_url":"https://github.com/FlyTune/MASPO-RL/blob/HEAD/recipe/r1/reward_score.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":"8a84f8cc921357e2","mcp_get_code":{"code_sha256":"8a84f8cc921357e2"}},{"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/recipe/r1/reward_score.py","file_url":"https://github.com/wdqqdw/Echo/blob/HEAD/verl/recipe/r1/reward_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"arxiv_id":"2601.21468","paper":"/paper/arxiv-2601-21468","title":"MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"meituan/MemOCR","path":"recipe/r1/reward_score.py","file_url":"https://github.com/meituan/MemOCR/blob/HEAD/recipe/r1/reward_score.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":"8a84f8cc921357e2","mcp_get_code":{"code_sha256":"8a84f8cc921357e2"}},{"arxiv_id":"2601.18533","paper":"/paper/arxiv-2601-18533","title":"From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"YJiangcm/RLVRR","path":"openrlhf/reward_tools/reward_fn.py","file_url":"https://github.com/YJiangcm/RLVRR/blob/HEAD/openrlhf/reward_tools/reward_fn.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"6e9c69dc6dfeb4ae","mcp_get_code":{"code_sha256":"6e9c69dc6dfeb4ae"}},{"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/recipe/r1/reward_score.py","file_url":"https://github.com/HowardLi1984/ChemCraft/blob/HEAD/chemcraft_rl/recipe/r1/reward_score.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":"8a84f8cc921357e2","mcp_get_code":{"code_sha256":"8a84f8cc921357e2"}},{"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":"recipe/r1/reward_score.py","file_url":"https://github.com/langfengQ/AgentOCR/blob/HEAD/recipe/r1/reward_score.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":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"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/recipe/r1/reward_score.py","file_url":"https://github.com/zzfoutofspace/ATPO/blob/HEAD/ATPO/verl_atpo/recipe/r1/reward_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"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":"recipe/r1/reward_score.py","file_url":"https://github.com/SII-zyj/Ophiuchus/blob/HEAD/recipe/r1/reward_score.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":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"arxiv_id":"2512.11391","paper":"/paper/arxiv-2512-11391","title":"Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimization","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"ivanniu/NSPO","path":"verl/recipe/r1/reward_score.py","file_url":"https://github.com/ivanniu/NSPO/blob/HEAD/verl/recipe/r1/reward_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"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":"recipe/r1/reward_score.py","file_url":"https://github.com/mzf666/MATPO/blob/HEAD/recipe/r1/reward_score.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":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"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/recipe/r1/reward_score.py","file_url":"https://github.com/bytedance/EvoQuality/blob/HEAD/verl/recipe/r1/reward_score.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":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"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":"recipe/r1/reward_score.py","file_url":"https://github.com/xid32/SoundMind/blob/HEAD/recipe/r1/reward_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"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/recipe/r1/reward_score.py","file_url":"https://github.com/bigai-nlco/rulereasoner/blob/HEAD/verl/recipe/r1/reward_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"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/recipe/r1/reward_score.py","file_url":"https://github.com/lezhang7/rearank/blob/HEAD/verl/recipe/r1/reward_score.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":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"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":"recipe/r1/reward_score.py","file_url":"https://github.com/visual-agent/deepeyes/blob/HEAD/recipe/r1/reward_score.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":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"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/recipe/r1/reward_score.py","file_url":"https://github.com/prime-rl/ttrl/blob/HEAD/verl/recipe/r1/reward_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"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/utils/reward_score/explore_tom_2.py","file_url":"https://github.com/bigai-ai/ToM-RL/blob/HEAD/verl/utils/reward_score/explore_tom_2.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a5c20c9ff16e297d","mcp_get_code":{"code_sha256":"a5c20c9ff16e297d"}},{"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":"recipe/r1/reward_score.py","file_url":"https://github.com/snu-mllab/guided-rest/blob/HEAD/recipe/r1/reward_score.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":"8a84f8cc921357e2","mcp_get_code":{"code_sha256":"8a84f8cc921357e2"}},{"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":"recipe/r1/reward_score.py","file_url":"https://github.com/du-nlp-lab/lengthreward/blob/HEAD/recipe/r1/reward_score.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":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"arxiv_id":"2107.11587","paper":"/paper/model-based-micro-data-reinforcement-learning-1","title":"Model-based micro-data reinforcement learning: what are the crucial model properties and which model to choose?","date":"2021-07-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ramp-kits/rl_simulator","path":"benchmark/acrobot/reward_function.py","file_url":"https://github.com/ramp-kits/rl_simulator/blob/HEAD/benchmark/acrobot/reward_function.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":false,"code_sha256_prefix":"d5e9182e08dfe611","mcp_get_code":{"code_sha256":"d5e9182e08dfe611"}},{"arxiv_id":"2004.09395","paper":"/paper/energy-based-imitation-learning","title":"Energy-Based Imitation Learning","date":"2020-04-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apexrl/EBIL-torch","path":"rlkit/torch/ebil/ebil.py","file_url":"https://github.com/apexrl/EBIL-torch/blob/HEAD/rlkit/torch/ebil/ebil.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f97c59ae63058414","mcp_get_code":{"code_sha256":"f97c59ae63058414"}},{"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":"recipe/r1/reward_score.py","file_url":"https://github.com/liziniu/KnapsackRL/blob/HEAD/recipe/r1/reward_score.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":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"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":"recipe/r1/reward_score.py","file_url":"https://github.com/Tunanzzz/Meerkat-VL/blob/HEAD/recipe/r1/reward_score.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":"8a84f8cc921357e2","mcp_get_code":{"code_sha256":"8a84f8cc921357e2"}},{"arxiv_id":"openreview_Tkdgg5uqNK","paper":null,"title":"arXiv:openreview_Tkdgg5uqNK","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"ZhijianZhou/Disppo","path":"recipe/r1/reward_score.py","file_url":"https://github.com/ZhijianZhou/Disppo/blob/HEAD/recipe/r1/reward_score.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":"c30b2a96103abd2c","mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}}]}