{"adoption": {"forks": 216, "observed_at": "2026-08-28T04:06:31.402415+00:00", "stars": 2256}, "canonical_url": "https://ross.abutalabs.com/products/verl-agent", "card": {"archived": false, "artifact_type": "framework", "description": "verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper \"Group-in-Group Policy Optimization for LLM Agent Training\"", "domain": ["reinforcement-learning", "large-language-models", "machine-learning", "deep-learning"], "enriched": true, "function": ["llm-training", "reinforcement-learning", "agent-framework", "machine-learning"], "health_score": 88, "homepage": "https://huggingface.co/papers/2505.10978", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["langfengQ/verl-agent"], "name": "langfengQ/verl-agent", "platform": ["python"], "pushed_at": "2026-06-09T13:35:49+00:00", "repo": "langfengQ/verl-agent", "stars": 2256, "tags": ["rl-training", "grpo", "gigpo", "multi-turn-agents", "verl", "llm-agents", "research-code", "ai-agents", "gpu", "linux"], "topics": ["llm-agents", "llm-training", "reinforcement-learning", "large-language-models", "deepseek-r1", "grpo", "agent-framework", "gigpo"], "urls": [], "use_cases": ["train llm agents with reinforcement learning", "implement gigpo for long-horizon agent training", "run multi-turn RL rollouts on ALFWorld or WebShop", "fine-tune Qwen models as interactive agents", "compare group-based RL algorithms like GRPO and GiGPO", "train vision-language agents in visual environments"], "what_it_is": "verl-agent is an extension of the veRL framework for training LLM and VLM agents via reinforcement learning, featuring step-independent multi-turn rollouts and customizable history/memory management. It is also the official implementation of the GiGPO (Group-in-Group Policy Optimization) algorithm for fine-grained credit assignment in long-horizon agent training.", "when_to_avoid": ["you only need single-turn RLHF or SFT without agent-environment interaction", "you need a production inference or serving framework rather than a training framework", "you lack GPU resources for large-scale RL rollouts"], "when_to_choose": ["you need RL post-training of LLM agents over multi-turn, long-horizon tasks", "you want critic-free group-based RL with fine-grained step-level credit assignment", "you need customizable per-step input structures and memory modules during rollouts", "you want to reproduce or extend GiGPO, HGPO, or GraphGPO research"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/verl-agent", "repo": "langfengQ/verl-agent", "role": "main", "score": 56}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:31.402415+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:43:42.885487+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "37bad6a6e72d41137f3579d2f45e0e8ba5c95f00bfe62c8e63ec751b0bba00cd", "fetched_at": "2026-08-28T04:06:31.402415+00:00", "kind": "readme", "missing": false, "url": "https://github.com/langfengQ/verl-agent"}, {"content_hash": "fb194e7508b97163cba59aca4caf6bb9f2d2976d1078e3abe613f4e2ca32f531", "fetched_at": "2026-08-29T10:23:42.713766+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/papers/2505.10978"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T10:23:42.722887+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "de6b7a178be544927ffd2e1990e33adcbee1bf54f7edf74da0714c6a3803ec65", "fetched_at": "2026-08-29T10:23:42.724645+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/pricing"}, {"content_hash": "0a25e6fef2754432a25f89619cfd91095b9a7cac3a421f8f0214bdd6a9ceb316", "fetched_at": "2026-08-29T10:23:42.726958+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/huggingface"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:31.402415+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:43:42.885487+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "37bad6a6e72d41137f3579d2f45e0e8ba5c95f00bfe62c8e63ec751b0bba00cd", "fetched_at": "2026-08-28T04:06:31.402415+00:00", "kind": "readme", "missing": false, "url": "https://github.com/langfengQ/verl-agent"}, {"content_hash": "fb194e7508b97163cba59aca4caf6bb9f2d2976d1078e3abe613f4e2ca32f531", "fetched_at": "2026-08-29T10:23:42.713766+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/papers/2505.10978"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T10:23:42.722887+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "de6b7a178be544927ffd2e1990e33adcbee1bf54f7edf74da0714c6a3803ec65", "fetched_at": "2026-08-29T10:23:42.724645+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/pricing"}, {"content_hash": "0a25e6fef2754432a25f89619cfd91095b9a7cac3a421f8f0214bdd6a9ceb316", "fetched_at": "2026-08-29T10:23:42.726958+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/huggingface"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:43:42.885487+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "37bad6a6e72d41137f3579d2f45e0e8ba5c95f00bfe62c8e63ec751b0bba00cd", "fetched_at": "2026-08-28T04:06:31.402415+00:00", "kind": "readme", "missing": false, "url": "https://github.com/langfengQ/verl-agent"}, {"content_hash": "fb194e7508b97163cba59aca4caf6bb9f2d2976d1078e3abe613f4e2ca32f531", "fetched_at": "2026-08-29T10:23:42.713766+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/papers/2505.10978"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T10:23:42.722887+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "de6b7a178be544927ffd2e1990e33adcbee1bf54f7edf74da0714c6a3803ec65", "fetched_at": "2026-08-29T10:23:42.724645+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/pricing"}, {"content_hash": "0a25e6fef2754432a25f89619cfd91095b9a7cac3a421f8f0214bdd6a9ceb316", "fetched_at": "2026-08-29T10:23:42.726958+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/huggingface"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:31.402415+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:31.402415+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:31.402415+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:43:42.885487+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "37bad6a6e72d41137f3579d2f45e0e8ba5c95f00bfe62c8e63ec751b0bba00cd", "fetched_at": "2026-08-28T04:06:31.402415+00:00", "kind": "readme", "missing": false, "url": "https://github.com/langfengQ/verl-agent"}, {"content_hash": "fb194e7508b97163cba59aca4caf6bb9f2d2976d1078e3abe613f4e2ca32f531", "fetched_at": "2026-08-29T10:23:42.713766+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/papers/2505.10978"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T10:23:42.722887+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "de6b7a178be544927ffd2e1990e33adcbee1bf54f7edf74da0714c6a3803ec65", "fetched_at": "2026-08-29T10:23:42.724645+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/pricing"}, {"content_hash": "0a25e6fef2754432a25f89619cfd91095b9a7cac3a421f8f0214bdd6a9ceb316", "fetched_at": "2026-08-29T10:23:42.726958+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/huggingface"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:31.402415+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:31.402415+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:43:42.885487+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "37bad6a6e72d41137f3579d2f45e0e8ba5c95f00bfe62c8e63ec751b0bba00cd", "fetched_at": "2026-08-28T04:06:31.402415+00:00", "kind": "readme", "missing": false, "url": "https://github.com/langfengQ/verl-agent"}, {"content_hash": "fb194e7508b97163cba59aca4caf6bb9f2d2976d1078e3abe613f4e2ca32f531", "fetched_at": "2026-08-29T10:23:42.713766+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/papers/2505.10978"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T10:23:42.722887+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "de6b7a178be544927ffd2e1990e33adcbee1bf54f7edf74da0714c6a3803ec65", "fetched_at": "2026-08-29T10:23:42.724645+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/pricing"}, {"content_hash": "0a25e6fef2754432a25f89619cfd91095b9a7cac3a421f8f0214bdd6a9ceb316", "fetched_at": "2026-08-29T10:23:42.726958+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/huggingface"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:31.402415+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:31.402415+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:31.402415+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:43:42.885487+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "37bad6a6e72d41137f3579d2f45e0e8ba5c95f00bfe62c8e63ec751b0bba00cd", "fetched_at": "2026-08-28T04:06:31.402415+00:00", "kind": "readme", "missing": false, "url": "https://github.com/langfengQ/verl-agent"}, {"content_hash": "fb194e7508b97163cba59aca4caf6bb9f2d2976d1078e3abe613f4e2ca32f531", "fetched_at": "2026-08-29T10:23:42.713766+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/papers/2505.10978"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T10:23:42.722887+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "de6b7a178be544927ffd2e1990e33adcbee1bf54f7edf74da0714c6a3803ec65", "fetched_at": "2026-08-29T10:23:42.724645+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/pricing"}, {"content_hash": "0a25e6fef2754432a25f89619cfd91095b9a7cac3a421f8f0214bdd6a9ceb316", "fetched_at": "2026-08-29T10:23:42.726958+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/huggingface"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:31.402415+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:31.402415+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:43:42.885487+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "37bad6a6e72d41137f3579d2f45e0e8ba5c95f00bfe62c8e63ec751b0bba00cd", "fetched_at": "2026-08-28T04:06:31.402415+00:00", "kind": "readme", "missing": false, "url": "https://github.com/langfengQ/verl-agent"}, {"content_hash": "fb194e7508b97163cba59aca4caf6bb9f2d2976d1078e3abe613f4e2ca32f531", "fetched_at": "2026-08-29T10:23:42.713766+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/papers/2505.10978"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T10:23:42.722887+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "de6b7a178be544927ffd2e1990e33adcbee1bf54f7edf74da0714c6a3803ec65", "fetched_at": "2026-08-29T10:23:42.724645+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/pricing"}, {"content_hash": "0a25e6fef2754432a25f89619cfd91095b9a7cac3a421f8f0214bdd6a9ceb316", "fetched_at": "2026-08-29T10:23:42.726958+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/huggingface"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:43:42.885487+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "37bad6a6e72d41137f3579d2f45e0e8ba5c95f00bfe62c8e63ec751b0bba00cd", "fetched_at": "2026-08-28T04:06:31.402415+00:00", "kind": "readme", "missing": false, "url": "https://github.com/langfengQ/verl-agent"}, {"content_hash": "fb194e7508b97163cba59aca4caf6bb9f2d2976d1078e3abe613f4e2ca32f531", "fetched_at": "2026-08-29T10:23:42.713766+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/papers/2505.10978"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T10:23:42.722887+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "de6b7a178be544927ffd2e1990e33adcbee1bf54f7edf74da0714c6a3803ec65", "fetched_at": "2026-08-29T10:23:42.724645+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/pricing"}, {"content_hash": "0a25e6fef2754432a25f89619cfd91095b9a7cac3a421f8f0214bdd6a9ceb316", "fetched_at": "2026-08-29T10:23:42.726958+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/huggingface"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:43:42.885487+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "37bad6a6e72d41137f3579d2f45e0e8ba5c95f00bfe62c8e63ec751b0bba00cd", "fetched_at": "2026-08-28T04:06:31.402415+00:00", "kind": "readme", "missing": false, "url": "https://github.com/langfengQ/verl-agent"}, {"content_hash": "fb194e7508b97163cba59aca4caf6bb9f2d2976d1078e3abe613f4e2ca32f531", "fetched_at": "2026-08-29T10:23:42.713766+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/papers/2505.10978"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T10:23:42.722887+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "de6b7a178be544927ffd2e1990e33adcbee1bf54f7edf74da0714c6a3803ec65", "fetched_at": "2026-08-29T10:23:42.724645+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/pricing"}, {"content_hash": "0a25e6fef2754432a25f89619cfd91095b9a7cac3a421f8f0214bdd6a9ceb316", "fetched_at": "2026-08-29T10:23:42.726958+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/huggingface"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:43:42.885487+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "37bad6a6e72d41137f3579d2f45e0e8ba5c95f00bfe62c8e63ec751b0bba00cd", "fetched_at": "2026-08-28T04:06:31.402415+00:00", "kind": "readme", "missing": false, "url": "https://github.com/langfengQ/verl-agent"}, {"content_hash": "fb194e7508b97163cba59aca4caf6bb9f2d2976d1078e3abe613f4e2ca32f531", "fetched_at": "2026-08-29T10:23:42.713766+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/papers/2505.10978"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T10:23:42.722887+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "de6b7a178be544927ffd2e1990e33adcbee1bf54f7edf74da0714c6a3803ec65", "fetched_at": "2026-08-29T10:23:42.724645+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/pricing"}, {"content_hash": "0a25e6fef2754432a25f89619cfd91095b9a7cac3a421f8f0214bdd6a9ceb316", "fetched_at": "2026-08-29T10:23:42.726958+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/huggingface"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 86, "longevity": 37, "rhythm": 28}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 528, "days_push": 85, "days_rel": 265, "gap_med": null, "n_releases_24m": 1}, "score": 56, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}