{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AMEYCFOFDS7DDKK5LIXISBGABK","short_pith_number":"pith:AMEYCFOF","schema_version":"1.0","canonical_sha256":"03098115c51cbe31a95d5a2e8904c00ab0853bb61b7ef9d939e84fefd5dd9ed0","source":{"kind":"arxiv","id":"2406.04151","version":1},"attestation_state":"computed","paper":{"title":"AgentGym: Evolving Large Language Model-based Agents across Diverse Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Boyang Hong, Chenyang Liao, Dingwen Yang, Honglin Guo, Junzhe Wang, Lu Chen, Qi Zhang, Rui Zheng, Songyang Gao, Tao Gui, Wei He, Wenxiang Chen, Xin Guo, Xipeng Qiu, Xuanjing Huang, Yicheng Zou, Yiwen Ding, Yu-Gang Jiang, Zhiheng Xi, Zuxuan Wu","submitted_at":"2024-06-06T15:15:41Z","abstract_excerpt":"Building generalist agents that can handle diverse tasks and evolve themselves across different environments is a long-term goal in the AI community. Large language models (LLMs) are considered a promising foundation to build such agents due to their generalized capabilities. Current approaches either have LLM-based agents imitate expert-provided trajectories step-by-step, requiring human supervision, which is hard to scale and limits environmental exploration; or they let agents explore and learn in isolated environments, resulting in specialist agents with limited generalization. In this pap"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.04151","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-06T15:15:41Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5237ec64e98ef380bec4234825475ae04e40349c5b3b012c065a8d7d24daabca","abstract_canon_sha256":"d27de88f67fb9461c1518b386502324b7364bdbf41c9ae26644aa2751215221b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:21.497824Z","signature_b64":"WCdWOlGsn0C3TrawZX+2KHMq7e0N8XDFC0Hv1O9wl2xjopaPez7r6FFHCUcQBkP1Ywm6cfWL4BvNpQb0K3y/BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03098115c51cbe31a95d5a2e8904c00ab0853bb61b7ef9d939e84fefd5dd9ed0","last_reissued_at":"2026-07-05T08:28:21.497359Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:21.497359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AgentGym: Evolving Large Language Model-based Agents across Diverse Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Boyang Hong, Chenyang Liao, Dingwen Yang, Honglin Guo, Junzhe Wang, Lu Chen, Qi Zhang, Rui Zheng, Songyang Gao, Tao Gui, Wei He, Wenxiang Chen, Xin Guo, Xipeng Qiu, Xuanjing Huang, Yicheng Zou, Yiwen Ding, Yu-Gang Jiang, Zhiheng Xi, Zuxuan Wu","submitted_at":"2024-06-06T15:15:41Z","abstract_excerpt":"Building generalist agents that can handle diverse tasks and evolve themselves across different environments is a long-term goal in the AI community. Large language models (LLMs) are considered a promising foundation to build such agents due to their generalized capabilities. Current approaches either have LLM-based agents imitate expert-provided trajectories step-by-step, requiring human supervision, which is hard to scale and limits environmental exploration; or they let agents explore and learn in isolated environments, resulting in specialist agents with limited generalization. In this pap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04151","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.04151/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.04151","created_at":"2026-07-05T08:28:21.497419+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04151v1","created_at":"2026-07-05T08:28:21.497419+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04151","created_at":"2026-07-05T08:28:21.497419+00:00"},{"alias_kind":"pith_short_12","alias_value":"AMEYCFOFDS7D","created_at":"2026-07-05T08:28:21.497419+00:00"},{"alias_kind":"pith_short_16","alias_value":"AMEYCFOFDS7DDKK5","created_at":"2026-07-05T08:28:21.497419+00:00"},{"alias_kind":"pith_short_8","alias_value":"AMEYCFOF","created_at":"2026-07-05T08:28:21.497419+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06503","citing_title":"Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2606.02372","citing_title":"COMAP: Co-Evolving World Models and Agent Policies for LLM Agents","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31365","citing_title":"Learning to Adapt: Self-Improving Web Agent via Cognitive-Aware Exploration","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24426","citing_title":"SEAL: Synergistic Co-Evolution of Agents and Learning Environments","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24828","citing_title":"Test-Time Deep Thinking to Explore Implicit Rules","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2510.13727","citing_title":"From Refusal to Recovery: A Control-Theoretic Approach to Generative AI Guardrails","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2408.07199","citing_title":"Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2501.09686","citing_title":"Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models","ref_index":166,"is_internal_anchor":false},{"citing_arxiv_id":"2508.06471","citing_title":"GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AMEYCFOFDS7DDKK5LIXISBGABK","json":"https://pith.science/pith/AMEYCFOFDS7DDKK5LIXISBGABK.json","graph_json":"https://pith.science/api/pith-number/AMEYCFOFDS7DDKK5LIXISBGABK/graph.json","events_json":"https://pith.science/api/pith-number/AMEYCFOFDS7DDKK5LIXISBGABK/events.json","paper":"https://pith.science/paper/AMEYCFOF"},"agent_actions":{"view_html":"https://pith.science/pith/AMEYCFOFDS7DDKK5LIXISBGABK","download_json":"https://pith.science/pith/AMEYCFOFDS7DDKK5LIXISBGABK.json","view_paper":"https://pith.science/paper/AMEYCFOF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04151&json=true","fetch_graph":"https://pith.science/api/pith-number/AMEYCFOFDS7DDKK5LIXISBGABK/graph.json","fetch_events":"https://pith.science/api/pith-number/AMEYCFOFDS7DDKK5LIXISBGABK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AMEYCFOFDS7DDKK5LIXISBGABK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AMEYCFOFDS7DDKK5LIXISBGABK/action/storage_attestation","attest_author":"https://pith.science/pith/AMEYCFOFDS7DDKK5LIXISBGABK/action/author_attestation","sign_citation":"https://pith.science/pith/AMEYCFOFDS7DDKK5LIXISBGABK/action/citation_signature","submit_replication":"https://pith.science/pith/AMEYCFOFDS7DDKK5LIXISBGABK/action/replication_record"}},"created_at":"2026-07-05T08:28:21.497419+00:00","updated_at":"2026-07-05T08:28:21.497419+00:00"}