{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HODV7EKFSHTMAY5EHWFYM37TCF","short_pith_number":"pith:HODV7EKF","canonical_record":{"source":{"id":"2509.08755","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-10T16:46:11Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"adf6cd3636adabfcd4166c4d1e17e5d8d49ceecfa2201e666742a2cfa69940ff","abstract_canon_sha256":"4f4d9e8b34fd2ff27aba8278152b6c1c7747cbc7f6dc704c920e668d6488d793"},"schema_version":"1.0"},"canonical_sha256":"3b875f914591e6c063a43d8b866ff311508b0e801de4107aed9682c46d47e8bd","source":{"kind":"arxiv","id":"2509.08755","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.08755","created_at":"2026-07-05T12:08:35Z"},{"alias_kind":"arxiv_version","alias_value":"2509.08755v1","created_at":"2026-07-05T12:08:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08755","created_at":"2026-07-05T12:08:35Z"},{"alias_kind":"pith_short_12","alias_value":"HODV7EKFSHTM","created_at":"2026-07-05T12:08:35Z"},{"alias_kind":"pith_short_16","alias_value":"HODV7EKFSHTMAY5E","created_at":"2026-07-05T12:08:35Z"},{"alias_kind":"pith_short_8","alias_value":"HODV7EKF","created_at":"2026-07-05T12:08:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HODV7EKFSHTMAY5EHWFYM37TCF","target":"record","payload":{"canonical_record":{"source":{"id":"2509.08755","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-10T16:46:11Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"adf6cd3636adabfcd4166c4d1e17e5d8d49ceecfa2201e666742a2cfa69940ff","abstract_canon_sha256":"4f4d9e8b34fd2ff27aba8278152b6c1c7747cbc7f6dc704c920e668d6488d793"},"schema_version":"1.0"},"canonical_sha256":"3b875f914591e6c063a43d8b866ff311508b0e801de4107aed9682c46d47e8bd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:35.640083Z","signature_b64":"dRLECOcgLdWdJxNto+JP4x4K/BQNUyGvaMrtDrNW8IQ8NldjwOY3txM2QgC/0n6lllKZBHI1VUL+GBY+AWPOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b875f914591e6c063a43d8b866ff311508b0e801de4107aed9682c46d47e8bd","last_reissued_at":"2026-07-05T12:08:35.639501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:35.639501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.08755","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:08:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YUjnUArqXdgQEDXWx3ixwLE5VF+I9sf13blm24CE5m88Jovz+AwAIcBCT7ThRG1wbz3e9niQiDm88/wuKnK6Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T02:37:03.173233Z"},"content_sha256":"104e1193ea04f482290b5dedcfac0dfa46e99799e82c806f5a88e9eacc7dc394","schema_version":"1.0","event_id":"sha256:104e1193ea04f482290b5dedcfac0dfa46e99799e82c806f5a88e9eacc7dc394"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HODV7EKFSHTMAY5EHWFYM37TCF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Baodai Huang, Chenyang Liao, Guanyu Li, Honglin Guo, Jiaqi Liu, Jiazheng Zhang, Jiecao Chen, Jixuan Huang, Junjie Ye, Qi Zhang, Rui Zheng, Tao Gui, Wei He, Wenxiang Chen, Xuanjing Huang, Xuesong Yao, Yiwen Ding, Yufei Xu, Yu-Gang Jiang, Zehui Chen, Zhengyin Du, Zhiheng Xi, Zuxuan Wu","submitted_at":"2025-09-10T16:46:11Z","abstract_excerpt":"Developing autonomous LLM agents capable of making a series of intelligent decisions to solve complex, real-world tasks is a fast-evolving frontier. Like human cognitive development, agents are expected to acquire knowledge and skills through exploration and interaction with the environment. Despite advances, the community still lacks a unified, interactive reinforcement learning (RL) framework that can effectively train such agents from scratch -- without relying on supervised fine-tuning (SFT) -- across diverse and realistic environments. To bridge this gap, we introduce AgentGym-RL, a new f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08755","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/2509.08755/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:08:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VvUnWchVAjabSxzgBjrrarmcI8Y2UzvjpdiwMfLjs4JG2tQCl1+nEbP82fROU+5c9fAlOuCguXMH4Q9qnFoKBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T02:37:03.173633Z"},"content_sha256":"7c677d4b69f435764afebe6ad7342dd667038fc3679634fe7ddd390b8904f7f0","schema_version":"1.0","event_id":"sha256:7c677d4b69f435764afebe6ad7342dd667038fc3679634fe7ddd390b8904f7f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HODV7EKFSHTMAY5EHWFYM37TCF/bundle.json","state_url":"https://pith.science/pith/HODV7EKFSHTMAY5EHWFYM37TCF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HODV7EKFSHTMAY5EHWFYM37TCF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-27T02:37:03Z","links":{"resolver":"https://pith.science/pith/HODV7EKFSHTMAY5EHWFYM37TCF","bundle":"https://pith.science/pith/HODV7EKFSHTMAY5EHWFYM37TCF/bundle.json","state":"https://pith.science/pith/HODV7EKFSHTMAY5EHWFYM37TCF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HODV7EKFSHTMAY5EHWFYM37TCF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HODV7EKFSHTMAY5EHWFYM37TCF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4f4d9e8b34fd2ff27aba8278152b6c1c7747cbc7f6dc704c920e668d6488d793","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-10T16:46:11Z","title_canon_sha256":"adf6cd3636adabfcd4166c4d1e17e5d8d49ceecfa2201e666742a2cfa69940ff"},"schema_version":"1.0","source":{"id":"2509.08755","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.08755","created_at":"2026-07-05T12:08:35Z"},{"alias_kind":"arxiv_version","alias_value":"2509.08755v1","created_at":"2026-07-05T12:08:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08755","created_at":"2026-07-05T12:08:35Z"},{"alias_kind":"pith_short_12","alias_value":"HODV7EKFSHTM","created_at":"2026-07-05T12:08:35Z"},{"alias_kind":"pith_short_16","alias_value":"HODV7EKFSHTMAY5E","created_at":"2026-07-05T12:08:35Z"},{"alias_kind":"pith_short_8","alias_value":"HODV7EKF","created_at":"2026-07-05T12:08:35Z"}],"graph_snapshots":[{"event_id":"sha256:7c677d4b69f435764afebe6ad7342dd667038fc3679634fe7ddd390b8904f7f0","target":"graph","created_at":"2026-07-05T12:08:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.08755/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Developing autonomous LLM agents capable of making a series of intelligent decisions to solve complex, real-world tasks is a fast-evolving frontier. Like human cognitive development, agents are expected to acquire knowledge and skills through exploration and interaction with the environment. Despite advances, the community still lacks a unified, interactive reinforcement learning (RL) framework that can effectively train such agents from scratch -- without relying on supervised fine-tuning (SFT) -- across diverse and realistic environments. To bridge this gap, we introduce AgentGym-RL, a new f","authors_text":"Baodai Huang, Chenyang Liao, Guanyu Li, Honglin Guo, Jiaqi Liu, Jiazheng Zhang, Jiecao Chen, Jixuan Huang, Junjie Ye, Qi Zhang, Rui Zheng, Tao Gui, Wei He, Wenxiang Chen, Xuanjing Huang, Xuesong Yao, Yiwen Ding, Yufei Xu, Yu-Gang Jiang, Zehui Chen, Zhengyin Du, Zhiheng Xi, Zuxuan Wu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-10T16:46:11Z","title":"AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08755","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:104e1193ea04f482290b5dedcfac0dfa46e99799e82c806f5a88e9eacc7dc394","target":"record","created_at":"2026-07-05T12:08:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4f4d9e8b34fd2ff27aba8278152b6c1c7747cbc7f6dc704c920e668d6488d793","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-10T16:46:11Z","title_canon_sha256":"adf6cd3636adabfcd4166c4d1e17e5d8d49ceecfa2201e666742a2cfa69940ff"},"schema_version":"1.0","source":{"id":"2509.08755","kind":"arxiv","version":1}},"canonical_sha256":"3b875f914591e6c063a43d8b866ff311508b0e801de4107aed9682c46d47e8bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b875f914591e6c063a43d8b866ff311508b0e801de4107aed9682c46d47e8bd","first_computed_at":"2026-07-05T12:08:35.639501Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:08:35.639501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dRLECOcgLdWdJxNto+JP4x4K/BQNUyGvaMrtDrNW8IQ8NldjwOY3txM2QgC/0n6lllKZBHI1VUL+GBY+AWPOCg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:08:35.640083Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.08755","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:104e1193ea04f482290b5dedcfac0dfa46e99799e82c806f5a88e9eacc7dc394","sha256:7c677d4b69f435764afebe6ad7342dd667038fc3679634fe7ddd390b8904f7f0"],"state_sha256":"f856d3626738a604f69d94944de9e30ac77e924223e4c69fab4698fe02528539"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gPDn5vXPzyEDSA1HoAG6JB0DeY97AuB1Rr9xTVthYQObVvMjFIdV5XwDYm56teOy4huNtyR5gFnW9fu5eVNfDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-27T02:37:03.176040Z","bundle_sha256":"8677ed57c20aaabec72ea95af526ec9865fbcb88f577a3268b41bfc9cdc5c96d"}}