{"adoption": {"forks": 60, "observed_at": "2026-08-28T04:03:37.290946+00:00", "stars": 1109}, "canonical_url": "https://ross.abutalabs.com/products/arpo", "card": {"archived": false, "artifact_type": "library", "description": "[ICLR 2026] Agentic Reinforced Policy Optimization (ARPO)", "domain": ["large-language-models", "reinforcement-learning", "machine-learning"], "enriched": true, "function": ["llm-training", "reinforcement-learning", "agent-framework"], "health_score": 93, "homepage": null, "language": "Python", "license": null, "license_family": "other", "maturity": "active", "member_repos": ["RUC-NLPIR/ARPO"], "name": "RUC-NLPIR/ARPO", "platform": ["python"], "pushed_at": "2026-08-20T07:12:37+00:00", "repo": "RUC-NLPIR/ARPO", "stars": 1109, "tags": ["rlhf", "policy-optimization", "agentic-rl", "iclr-2026", "research-code", "llm-post-training", "ai-agents", "gpu", "linux"], "topics": [], "urls": [], "use_cases": ["train llm agents with reinforcement learning", "improve multi-turn tool use of a language model", "reproduce ARPO paper results", "fine-tune Qwen or Llama models for agentic search", "apply RL post-training to deep search agents"], "what_it_is": "ARPO (Agentic Reinforced Policy Optimization) is a reinforcement learning algorithm and training framework for LLM agents, published at ICLR 2026. It provides training code, models, and datasets for improving multi-turn agentic reasoning and tool use via RL.", "when_to_avoid": ["you need a production-supported training framework with commercial support", "you need simple SFT-only fine-tuning without RL", "you lack GPU infrastructure for large-model RL training"], "when_to_choose": ["you need a research-grade agentic RL training algorithm for LLMs", "you want to RL-train models for multi-turn tool calling or deep search", "you want to build on ICLR 2026 ARPO/AEPO methods"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/arpo", "repo": "RUC-NLPIR/ARPO", "role": "main", "score": 54}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:37.290946+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:43:33.058581+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "08ad020623009d6342e028dba2e65eca535e6a96b7875e2f6bb52ef47202e72a", "fetched_at": "2026-08-28T04:03:37.290946+00:00", "kind": "readme", "missing": false, "url": "https://github.com/RUC-NLPIR/ARPO"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:37.290946+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:43:33.058581+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "08ad020623009d6342e028dba2e65eca535e6a96b7875e2f6bb52ef47202e72a", "fetched_at": "2026-08-28T04:03:37.290946+00:00", "kind": "readme", "missing": false, "url": "https://github.com/RUC-NLPIR/ARPO"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:43:33.058581+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "08ad020623009d6342e028dba2e65eca535e6a96b7875e2f6bb52ef47202e72a", "fetched_at": "2026-08-28T04:03:37.290946+00:00", "kind": "readme", "missing": false, "url": "https://github.com/RUC-NLPIR/ARPO"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:37.290946+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:37.290946+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:37.290946+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:43:33.058581+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "08ad020623009d6342e028dba2e65eca535e6a96b7875e2f6bb52ef47202e72a", "fetched_at": "2026-08-28T04:03:37.290946+00:00", "kind": "readme", "missing": false, "url": "https://github.com/RUC-NLPIR/ARPO"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:37.290946+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:37.290946+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:43:33.058581+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "08ad020623009d6342e028dba2e65eca535e6a96b7875e2f6bb52ef47202e72a", "fetched_at": "2026-08-28T04:03:37.290946+00:00", "kind": "readme", "missing": false, "url": "https://github.com/RUC-NLPIR/ARPO"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:37.290946+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:37.290946+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:37.290946+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:43:33.058581+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "08ad020623009d6342e028dba2e65eca535e6a96b7875e2f6bb52ef47202e72a", "fetched_at": "2026-08-28T04:03:37.290946+00:00", "kind": "readme", "missing": false, "url": "https://github.com/RUC-NLPIR/ARPO"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:37.290946+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:37.290946+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:43:33.058581+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "08ad020623009d6342e028dba2e65eca535e6a96b7875e2f6bb52ef47202e72a", "fetched_at": "2026-08-28T04:03:37.290946+00:00", "kind": "readme", "missing": false, "url": "https://github.com/RUC-NLPIR/ARPO"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:43:33.058581+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "08ad020623009d6342e028dba2e65eca535e6a96b7875e2f6bb52ef47202e72a", "fetched_at": "2026-08-28T04:03:37.290946+00:00", "kind": "readme", "missing": false, "url": "https://github.com/RUC-NLPIR/ARPO"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:43:33.058581+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "08ad020623009d6342e028dba2e65eca535e6a96b7875e2f6bb52ef47202e72a", "fetched_at": "2026-08-28T04:03:37.290946+00:00", "kind": "readme", "missing": false, "url": "https://github.com/RUC-NLPIR/ARPO"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:43:33.058581+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "08ad020623009d6342e028dba2e65eca535e6a96b7875e2f6bb52ef47202e72a", "fetched_at": "2026-08-28T04:03:37.290946+00:00", "kind": "readme", "missing": false, "url": "https://github.com/RUC-NLPIR/ARPO"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 98, "longevity": 29, "rhythm": 13}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 407, "days_push": 13, "days_rel": 367, "gap_med": null, "n_releases_24m": 1}, "score": 54, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}