{"adoption": {"forks": 70, "observed_at": "2026-08-28T04:04:44.380364+00:00", "stars": 1441}, "canonical_url": "https://ross.abutalabs.com/products/awesome-rl-based-reasoning-mllms", "card": {"archived": false, "artifact_type": "learning-resource", "description": "This repository provides valuable reference for researchers in the field of multimodality, please start your exploratory travel in RL-based Reasoning MLLMs!", "domain": ["artificial-intelligence", "large-language-models", "machine-learning", "awesome-lists", "tutorials"], "enriched": true, "function": ["machine-learning", "deep-learning", "llm-training", "documentation"], "health_score": 77, "homepage": null, "language": null, "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["Sun-Haoyuan23/Awesome-RL-based-Reasoning-MLLMs"], "name": "Sun-Haoyuan23/Awesome-RL-based-Reasoning-MLLMs", "platform": [], "pushed_at": "2026-08-02T03:59:51+00:00", "repo": "Sun-Haoyuan23/Awesome-RL-based-Reasoning-MLLMs", "stars": 1441, "tags": ["awesome-list", "multimodal", "reinforcement-learning", "reasoning", "mllm", "research-papers", "curated-list", "web-server"], "topics": [], "urls": [], "use_cases": ["find papers on RL-based reasoning for multimodal LLMs", "survey reinforcement fine-tuning of MLLMs", "research multimodal reasoning model landscape", "get started with RL reasoning research in multimodality", "track recent RFT papers for vision-language models", "prepare a literature review on multimodal reasoning"], "what_it_is": "A curated awesome-list repository collecting papers and resources on reinforcement learning-based reasoning for multimodal large language models (MLLMs). It tracks research works sorted by release date and includes a position paper summarizing the field.", "when_to_avoid": ["you need runnable code or training frameworks rather than a paper list", "you want RL reasoning resources for text-only LLMs", "you need a maintained software library"], "when_to_choose": ["you are a researcher surveying RL-based reasoning in multimodal LLMs", "you need a curated, time-sorted list of RFT/MLLM papers", "you want an entry point into the multimodal reasoning field"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/awesome-rl-based-reasoning-mllms", "repo": "Sun-Haoyuan23/Awesome-RL-based-Reasoning-MLLMs", "role": "main", "score": 63}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:44.380364+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:36:27.199075+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8ab32fa64a2eb006b9d932edfab3184fbe1c8b6bab53d4aeb2f40a5605874d9a", "fetched_at": "2026-08-28T04:04:44.380364+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Sun-Haoyuan23/Awesome-RL-based-Reasoning-MLLMs"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:44.380364+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:36:27.199075+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8ab32fa64a2eb006b9d932edfab3184fbe1c8b6bab53d4aeb2f40a5605874d9a", "fetched_at": "2026-08-28T04:04:44.380364+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Sun-Haoyuan23/Awesome-RL-based-Reasoning-MLLMs"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:36:27.199075+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8ab32fa64a2eb006b9d932edfab3184fbe1c8b6bab53d4aeb2f40a5605874d9a", "fetched_at": "2026-08-28T04:04:44.380364+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Sun-Haoyuan23/Awesome-RL-based-Reasoning-MLLMs"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:44.380364+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:44.380364+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:44.380364+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:36:27.199075+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8ab32fa64a2eb006b9d932edfab3184fbe1c8b6bab53d4aeb2f40a5605874d9a", "fetched_at": "2026-08-28T04:04:44.380364+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Sun-Haoyuan23/Awesome-RL-based-Reasoning-MLLMs"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:44.380364+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:44.380364+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:36:27.199075+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8ab32fa64a2eb006b9d932edfab3184fbe1c8b6bab53d4aeb2f40a5605874d9a", "fetched_at": "2026-08-28T04:04:44.380364+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Sun-Haoyuan23/Awesome-RL-based-Reasoning-MLLMs"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:44.380364+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:44.380364+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:44.380364+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:36:27.199075+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8ab32fa64a2eb006b9d932edfab3184fbe1c8b6bab53d4aeb2f40a5605874d9a", "fetched_at": "2026-08-28T04:04:44.380364+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Sun-Haoyuan23/Awesome-RL-based-Reasoning-MLLMs"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:44.380364+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:44.380364+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:36:27.199075+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8ab32fa64a2eb006b9d932edfab3184fbe1c8b6bab53d4aeb2f40a5605874d9a", "fetched_at": "2026-08-28T04:04:44.380364+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Sun-Haoyuan23/Awesome-RL-based-Reasoning-MLLMs"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:36:27.199075+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8ab32fa64a2eb006b9d932edfab3184fbe1c8b6bab53d4aeb2f40a5605874d9a", "fetched_at": "2026-08-28T04:04:44.380364+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Sun-Haoyuan23/Awesome-RL-based-Reasoning-MLLMs"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:36:27.199075+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8ab32fa64a2eb006b9d932edfab3184fbe1c8b6bab53d4aeb2f40a5605874d9a", "fetched_at": "2026-08-28T04:04:44.380364+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Sun-Haoyuan23/Awesome-RL-based-Reasoning-MLLMs"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:36:27.199075+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8ab32fa64a2eb006b9d932edfab3184fbe1c8b6bab53d4aeb2f40a5605874d9a", "fetched_at": "2026-08-28T04:04:44.380364+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Sun-Haoyuan23/Awesome-RL-based-Reasoning-MLLMs"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 95, "longevity": 39, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 558, "days_push": 31, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 63, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}