{"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/create-huggingface-actor","entry":"create_huggingface_actor","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":18,"n_papers_ran":18,"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":18,"n_places_pointer_only":1,"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":"2606.10646","paper":"/paper/arxiv-2606-10646","title":"How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Jiayi-Pan/TinyZero","path":"verl/utils/model.py","file_url":"https://github.com/Jiayi-Pan/TinyZero/blob/HEAD/verl/utils/model.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":"360c671d6041ba3b","mcp_get_code":{"code_sha256":"360c671d6041ba3b"}},{"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/utils/model.py","file_url":"https://github.com/Zhaolutuan/SAW/blob/HEAD/verl/utils/model.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":"360c671d6041ba3b","mcp_get_code":{"code_sha256":"360c671d6041ba3b"}},{"arxiv_id":"2602.15564","paper":"/paper/arxiv-2602-15564","title":"Beyond Static Pipelines: Learning Dynamic Workflows for Text-to-SQL","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Satissss/SquRL","path":"verl/utils/model.py","file_url":"https://github.com/Satissss/SquRL/blob/HEAD/verl/utils/model.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":"360c671d6041ba3b","mcp_get_code":{"code_sha256":"360c671d6041ba3b"}},{"arxiv_id":"2602.04417","paper":"/paper/arxiv-2602-04417","title":"EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"LunjunZhang/ema-pg","path":"search/verl/utils/model.py","file_url":"https://github.com/LunjunZhang/ema-pg/blob/HEAD/search/verl/utils/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"360c671d6041ba3b","mcp_get_code":{"code_sha256":"360c671d6041ba3b"}},{"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/utils/model.py","file_url":"https://github.com/Cherry-qwq/LcRL-Open/blob/HEAD/verl/utils/model.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":"360c671d6041ba3b","mcp_get_code":{"code_sha256":"360c671d6041ba3b"}},{"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/utils/model.py","file_url":"https://github.com/ulab-uiuc/ToMAP/blob/HEAD/verl/utils/model.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":"360c671d6041ba3b","mcp_get_code":{"code_sha256":"360c671d6041ba3b"}},{"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/utils/model.py","file_url":"https://github.com/gydpku/data_synthesis_rl/blob/HEAD/verl/utils/model.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":"360c671d6041ba3b","mcp_get_code":{"code_sha256":"360c671d6041ba3b"}},{"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/utils/model.py","file_url":"https://github.com/liumy2010/uft/blob/HEAD/verl/utils/model.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":"360c671d6041ba3b","mcp_get_code":{"code_sha256":"360c671d6041ba3b"}},{"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/utils/model.py","file_url":"https://github.com/vainf/thinkless/blob/HEAD/verl/verl/utils/model.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":"360c671d6041ba3b","mcp_get_code":{"code_sha256":"360c671d6041ba3b"}},{"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/utils/model.py","file_url":"https://github.com/zhyang2226/ar-lopti/blob/HEAD/verl/utils/model.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":"360c671d6041ba3b","mcp_get_code":{"code_sha256":"360c671d6041ba3b"}},{"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/utils/model.py","file_url":"https://github.com/salesforceairesearch/elastic-reasoning/blob/HEAD/verl/verl/utils/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"360c671d6041ba3b","mcp_get_code":{"code_sha256":"360c671d6041ba3b"}},{"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/utils/model.py","file_url":"https://github.com/alibaba-nlp/zerosearch/blob/HEAD/verl/utils/model.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":"360c671d6041ba3b","mcp_get_code":{"code_sha256":"360c671d6041ba3b"}},{"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/model.py","file_url":"https://github.com/bigai-ai/ToM-RL/blob/HEAD/verl/utils/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"360c671d6041ba3b","mcp_get_code":{"code_sha256":"360c671d6041ba3b"}},{"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/utils/model.py","file_url":"https://github.com/UCSB-NLP-Chang/ThinkPrune/blob/HEAD/verl/utils/model.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":"360c671d6041ba3b","mcp_get_code":{"code_sha256":"360c671d6041ba3b"}},{"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/utils/model.py","file_url":"https://github.com/Qihoo360/Light-R1/blob/HEAD/deepscaler-release/verl/verl/utils/model.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":"360c671d6041ba3b","mcp_get_code":{"code_sha256":"360c671d6041ba3b"}},{"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/utils/model.py","file_url":"https://github.com/Unakar/Logic-RL/blob/HEAD/verl/utils/model.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":"360c671d6041ba3b","mcp_get_code":{"code_sha256":"360c671d6041ba3b"}},{"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/utils/model.py","file_url":"https://github.com/qiancheng0/ToolRL/blob/HEAD/verl/utils/model.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":"360c671d6041ba3b","mcp_get_code":{"code_sha256":"360c671d6041ba3b"}},{"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/utils/model.py","file_url":"https://github.com/fzp0424/MT-R1-Zero/blob/HEAD/verl/utils/model.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":"360c671d6041ba3b","mcp_get_code":{"code_sha256":"360c671d6041ba3b"}}]}