{"adoption": {"forks": 133, "observed_at": "2026-08-28T04:06:55.349606+00:00", "stars": 2482}, "canonical_url": "https://ross.abutalabs.com/products/awesome-rl-for-lrms", "card": {"archived": false, "artifact_type": "learning-resource", "description": "A Survey of Reinforcement Learning for Large Reasoning Models", "domain": ["reinforcement-learning", "large-language-models", "artificial-intelligence", "tutorials", "awesome-lists"], "enriched": true, "function": ["reinforcement-learning", "llm-training", "machine-learning"], "health_score": 94, "homepage": "https://arxiv.org/abs/2509.08827", "language": "TeX", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["TsinghuaC3I/Awesome-RL-for-LRMs"], "name": "TsinghuaC3I/Awesome-RL-for-LRMs", "platform": ["cross-platform"], "pushed_at": "2026-08-20T13:22:49+00:00", "repo": "TsinghuaC3I/Awesome-RL-for-LRMs", "stars": 2482, "tags": ["awesome-list", "survey", "reasoning", "large-reasoning-models", "deepseek-r1", "paper-list", "rlhf"], "topics": ["awesome-list", "llm", "reasoning", "rl", "deepseek-r1", "open-source", "lrm"], "urls": [], "use_cases": ["find papers on RL for LLM reasoning", "survey reinforcement learning methods for large reasoning models", "research RL training after DeepSeek-R1", "find resources on RLHF and reasoning model training", "track recent research on LRM scalability and RL algorithms", "get started with academic literature on reasoning models"], "what_it_is": "A curated awesome-list accompanying the survey paper 'A Survey of Reinforcement Learning for Large Reasoning Models' from Tsinghua University. It catalogs research papers on applying reinforcement learning to LLMs and Large Reasoning Models (LRMs), organized by the survey's category structure.", "when_to_avoid": ["you need runnable training code or an RL framework rather than a paper list", "you want beginner tutorials rather than research papers"], "when_to_choose": ["you need a curated, categorized reading list of RL-for-reasoning research", "you are writing a literature review on LLM reasoning and RL", "you want to follow the state of the art since DeepSeek-R1"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/awesome-rl-for-lrms", "repo": "TsinghuaC3I/Awesome-RL-for-LRMs", "role": "main", "score": 57}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:55.349606+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:28:07.579482+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0136f4b840c53ab19402f7c5ecb294f4e813971051057261b895a76c83c09dd1", "fetched_at": "2026-08-28T04:06:55.349606+00:00", "kind": "readme", "missing": false, "url": "https://github.com/TsinghuaC3I/Awesome-RL-for-LRMs"}, {"content_hash": "eab8d22de1fa6f4163e53051d3f659f13f332c1ffe67c64bc93231d9377344a0", "fetched_at": "2026-08-29T10:10:03.125443+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2509.08827"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:10:03.132932+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:10:03.129322+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:10:03.135107+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:10:03.131166+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:55.349606+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:28:07.579482+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0136f4b840c53ab19402f7c5ecb294f4e813971051057261b895a76c83c09dd1", "fetched_at": "2026-08-28T04:06:55.349606+00:00", "kind": "readme", "missing": false, "url": "https://github.com/TsinghuaC3I/Awesome-RL-for-LRMs"}, {"content_hash": "eab8d22de1fa6f4163e53051d3f659f13f332c1ffe67c64bc93231d9377344a0", "fetched_at": "2026-08-29T10:10:03.125443+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2509.08827"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:10:03.132932+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:10:03.129322+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:10:03.135107+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:10:03.131166+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:28:07.579482+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0136f4b840c53ab19402f7c5ecb294f4e813971051057261b895a76c83c09dd1", "fetched_at": "2026-08-28T04:06:55.349606+00:00", "kind": "readme", "missing": false, "url": "https://github.com/TsinghuaC3I/Awesome-RL-for-LRMs"}, {"content_hash": "eab8d22de1fa6f4163e53051d3f659f13f332c1ffe67c64bc93231d9377344a0", "fetched_at": "2026-08-29T10:10:03.125443+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2509.08827"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:10:03.132932+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:10:03.129322+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:10:03.135107+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:10:03.131166+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:55.349606+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:55.349606+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:55.349606+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:28:07.579482+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0136f4b840c53ab19402f7c5ecb294f4e813971051057261b895a76c83c09dd1", "fetched_at": "2026-08-28T04:06:55.349606+00:00", "kind": "readme", "missing": false, "url": "https://github.com/TsinghuaC3I/Awesome-RL-for-LRMs"}, {"content_hash": "eab8d22de1fa6f4163e53051d3f659f13f332c1ffe67c64bc93231d9377344a0", "fetched_at": "2026-08-29T10:10:03.125443+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2509.08827"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:10:03.132932+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:10:03.129322+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:10:03.135107+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:10:03.131166+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:55.349606+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:55.349606+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:28:07.579482+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0136f4b840c53ab19402f7c5ecb294f4e813971051057261b895a76c83c09dd1", "fetched_at": "2026-08-28T04:06:55.349606+00:00", "kind": "readme", "missing": false, "url": "https://github.com/TsinghuaC3I/Awesome-RL-for-LRMs"}, {"content_hash": "eab8d22de1fa6f4163e53051d3f659f13f332c1ffe67c64bc93231d9377344a0", "fetched_at": "2026-08-29T10:10:03.125443+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2509.08827"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:10:03.132932+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:10:03.129322+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:10:03.135107+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:10:03.131166+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:55.349606+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:55.349606+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:55.349606+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:28:07.579482+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0136f4b840c53ab19402f7c5ecb294f4e813971051057261b895a76c83c09dd1", "fetched_at": "2026-08-28T04:06:55.349606+00:00", "kind": "readme", "missing": false, "url": "https://github.com/TsinghuaC3I/Awesome-RL-for-LRMs"}, {"content_hash": "eab8d22de1fa6f4163e53051d3f659f13f332c1ffe67c64bc93231d9377344a0", "fetched_at": "2026-08-29T10:10:03.125443+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2509.08827"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:10:03.132932+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:10:03.129322+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:10:03.135107+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:10:03.131166+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:55.349606+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:55.349606+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:28:07.579482+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0136f4b840c53ab19402f7c5ecb294f4e813971051057261b895a76c83c09dd1", "fetched_at": "2026-08-28T04:06:55.349606+00:00", "kind": "readme", "missing": false, "url": "https://github.com/TsinghuaC3I/Awesome-RL-for-LRMs"}, {"content_hash": "eab8d22de1fa6f4163e53051d3f659f13f332c1ffe67c64bc93231d9377344a0", "fetched_at": "2026-08-29T10:10:03.125443+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2509.08827"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:10:03.132932+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:10:03.129322+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:10:03.135107+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:10:03.131166+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:28:07.579482+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0136f4b840c53ab19402f7c5ecb294f4e813971051057261b895a76c83c09dd1", "fetched_at": "2026-08-28T04:06:55.349606+00:00", "kind": "readme", "missing": false, "url": "https://github.com/TsinghuaC3I/Awesome-RL-for-LRMs"}, {"content_hash": "eab8d22de1fa6f4163e53051d3f659f13f332c1ffe67c64bc93231d9377344a0", "fetched_at": "2026-08-29T10:10:03.125443+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2509.08827"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:10:03.132932+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:10:03.129322+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:10:03.135107+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:10:03.131166+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:28:07.579482+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0136f4b840c53ab19402f7c5ecb294f4e813971051057261b895a76c83c09dd1", "fetched_at": "2026-08-28T04:06:55.349606+00:00", "kind": "readme", "missing": false, "url": "https://github.com/TsinghuaC3I/Awesome-RL-for-LRMs"}, {"content_hash": "eab8d22de1fa6f4163e53051d3f659f13f332c1ffe67c64bc93231d9377344a0", "fetched_at": "2026-08-29T10:10:03.125443+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2509.08827"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:10:03.132932+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:10:03.129322+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:10:03.135107+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:10:03.131166+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:28:07.579482+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0136f4b840c53ab19402f7c5ecb294f4e813971051057261b895a76c83c09dd1", "fetched_at": "2026-08-28T04:06:55.349606+00:00", "kind": "readme", "missing": false, "url": "https://github.com/TsinghuaC3I/Awesome-RL-for-LRMs"}, {"content_hash": "eab8d22de1fa6f4163e53051d3f659f13f332c1ffe67c64bc93231d9377344a0", "fetched_at": "2026-08-29T10:10:03.125443+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2509.08827"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:10:03.132932+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:10:03.129322+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:10:03.135107+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:10:03.131166+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 98, "longevity": 37, "rhythm": 15}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 531, "days_push": 13, "days_rel": 357, "gap_med": null, "n_releases_24m": 1}, "score": 57, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}