{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XZEC4VZA2B74WLPEDUXQSGER7U","short_pith_number":"pith:XZEC4VZA","canonical_record":{"source":{"id":"2501.11425","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-20T11:46:04Z","cross_cats_sorted":[],"title_canon_sha256":"c9af14af427a15ed0696a16d26a1ec449eb91a4f3844465de1a7551a7ab1c5eb","abstract_canon_sha256":"fb26b0dff099292a23acc24014dcbe48910a591b4909dad189a51f83dac619f8"},"schema_version":"1.0"},"canonical_sha256":"be482e5720d07fcb2de41d2f091891fd2738851688e0a24d4e36ffb0c8545c06","source":{"kind":"arxiv","id":"2501.11425","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.11425","created_at":"2026-07-05T10:37:43Z"},{"alias_kind":"arxiv_version","alias_value":"2501.11425v3","created_at":"2026-07-05T10:37:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11425","created_at":"2026-07-05T10:37:43Z"},{"alias_kind":"pith_short_12","alias_value":"XZEC4VZA2B74","created_at":"2026-07-05T10:37:43Z"},{"alias_kind":"pith_short_16","alias_value":"XZEC4VZA2B74WLPE","created_at":"2026-07-05T10:37:43Z"},{"alias_kind":"pith_short_8","alias_value":"XZEC4VZA","created_at":"2026-07-05T10:37:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XZEC4VZA2B74WLPEDUXQSGER7U","target":"record","payload":{"canonical_record":{"source":{"id":"2501.11425","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-20T11:46:04Z","cross_cats_sorted":[],"title_canon_sha256":"c9af14af427a15ed0696a16d26a1ec449eb91a4f3844465de1a7551a7ab1c5eb","abstract_canon_sha256":"fb26b0dff099292a23acc24014dcbe48910a591b4909dad189a51f83dac619f8"},"schema_version":"1.0"},"canonical_sha256":"be482e5720d07fcb2de41d2f091891fd2738851688e0a24d4e36ffb0c8545c06","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:43.052986Z","signature_b64":"UH7OhXyfsqa2JKdBXQXekfH9DRM7nd8ohdSfKJwrdOB1ZFAVQCilwGej59yQ7KaVbMLAW8duNDRP5Azxc02DAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be482e5720d07fcb2de41d2f091891fd2738851688e0a24d4e36ffb0c8545c06","last_reissued_at":"2026-07-05T10:37:43.052070Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:43.052070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.11425","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:37:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cEfcNhZlh22tWxm51z0E16sgPGUFdwzZi6Z8Xm9260oCf4PlcJSxVMX1ub3v06C+pKAveBSGzS3tzN9zHKJXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T22:52:30.965635Z"},"content_sha256":"c9af07cc7495e039a0e9eb7cb424f4060a4255d9a19d8c0ef0a9265ce400f4c8","schema_version":"1.0","event_id":"sha256:c9af07cc7495e039a0e9eb7cb424f4060a4255d9a19d8c0ef0a9265ce400f4c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XZEC4VZA2B74WLPEDUXQSGER7U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiecao Chen, Junjie Ye, Siyu Yuan, Zehui Chen, Zhengyin Du, Zhiheng Xi","submitted_at":"2025-01-20T11:46:04Z","abstract_excerpt":"Large Language Models (LLMs) agents are increasingly pivotal for addressing complex tasks in interactive environments. Existing work mainly focuses on enhancing performance through behavior cloning from stronger experts, yet such approaches often falter in real-world applications, mainly due to the inability to recover from errors. However, step-level critique data is difficult and expensive to collect. Automating and dynamically constructing self-critique datasets is thus crucial to empowering models with intelligent agent capabilities. In this work, we propose an iterative self-training fram"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11425","kind":"arxiv","version":3},"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/2501.11425/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":"2026-07-05T10:37:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wkVGPk0B7TgeWNkNembSkzWQdpU1SOIeOnA1QPCdtbzRsNK+KkmcYhDw2n5GXeYF0Efy+WtmQSALSfdX3K/LBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T22:52:30.966232Z"},"content_sha256":"9c6483239fa049a37842fed43fd93099762d09afed51c6691a46cca351216f13","schema_version":"1.0","event_id":"sha256:9c6483239fa049a37842fed43fd93099762d09afed51c6691a46cca351216f13"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XZEC4VZA2B74WLPEDUXQSGER7U/bundle.json","state_url":"https://pith.science/pith/XZEC4VZA2B74WLPEDUXQSGER7U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XZEC4VZA2B74WLPEDUXQSGER7U/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":"2026-08-01T22:52:30Z","links":{"resolver":"https://pith.science/pith/XZEC4VZA2B74WLPEDUXQSGER7U","bundle":"https://pith.science/pith/XZEC4VZA2B74WLPEDUXQSGER7U/bundle.json","state":"https://pith.science/pith/XZEC4VZA2B74WLPEDUXQSGER7U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XZEC4VZA2B74WLPEDUXQSGER7U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XZEC4VZA2B74WLPEDUXQSGER7U","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":"fb26b0dff099292a23acc24014dcbe48910a591b4909dad189a51f83dac619f8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-20T11:46:04Z","title_canon_sha256":"c9af14af427a15ed0696a16d26a1ec449eb91a4f3844465de1a7551a7ab1c5eb"},"schema_version":"1.0","source":{"id":"2501.11425","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.11425","created_at":"2026-07-05T10:37:43Z"},{"alias_kind":"arxiv_version","alias_value":"2501.11425v3","created_at":"2026-07-05T10:37:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11425","created_at":"2026-07-05T10:37:43Z"},{"alias_kind":"pith_short_12","alias_value":"XZEC4VZA2B74","created_at":"2026-07-05T10:37:43Z"},{"alias_kind":"pith_short_16","alias_value":"XZEC4VZA2B74WLPE","created_at":"2026-07-05T10:37:43Z"},{"alias_kind":"pith_short_8","alias_value":"XZEC4VZA","created_at":"2026-07-05T10:37:43Z"}],"graph_snapshots":[{"event_id":"sha256:9c6483239fa049a37842fed43fd93099762d09afed51c6691a46cca351216f13","target":"graph","created_at":"2026-07-05T10:37:43Z","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/2501.11425/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) agents are increasingly pivotal for addressing complex tasks in interactive environments. Existing work mainly focuses on enhancing performance through behavior cloning from stronger experts, yet such approaches often falter in real-world applications, mainly due to the inability to recover from errors. However, step-level critique data is difficult and expensive to collect. Automating and dynamically constructing self-critique datasets is thus crucial to empowering models with intelligent agent capabilities. In this work, we propose an iterative self-training fram","authors_text":"Jiecao Chen, Junjie Ye, Siyu Yuan, Zehui Chen, Zhengyin Du, Zhiheng Xi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-20T11:46:04Z","title":"Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11425","kind":"arxiv","version":3},"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:c9af07cc7495e039a0e9eb7cb424f4060a4255d9a19d8c0ef0a9265ce400f4c8","target":"record","created_at":"2026-07-05T10:37:43Z","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":"fb26b0dff099292a23acc24014dcbe48910a591b4909dad189a51f83dac619f8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-20T11:46:04Z","title_canon_sha256":"c9af14af427a15ed0696a16d26a1ec449eb91a4f3844465de1a7551a7ab1c5eb"},"schema_version":"1.0","source":{"id":"2501.11425","kind":"arxiv","version":3}},"canonical_sha256":"be482e5720d07fcb2de41d2f091891fd2738851688e0a24d4e36ffb0c8545c06","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be482e5720d07fcb2de41d2f091891fd2738851688e0a24d4e36ffb0c8545c06","first_computed_at":"2026-07-05T10:37:43.052070Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:37:43.052070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UH7OhXyfsqa2JKdBXQXekfH9DRM7nd8ohdSfKJwrdOB1ZFAVQCilwGej59yQ7KaVbMLAW8duNDRP5Azxc02DAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:37:43.052986Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.11425","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9af07cc7495e039a0e9eb7cb424f4060a4255d9a19d8c0ef0a9265ce400f4c8","sha256:9c6483239fa049a37842fed43fd93099762d09afed51c6691a46cca351216f13"],"state_sha256":"f5d42847d79c275aff9125d4c0d142201c21a01ae8db858df18e226e706a4d87"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NeHU24kP9EjJjUx9FdzKU1UMMTj3aJD45MR509PNjsUvznBnJdkvT0E9Poij4ZXU2Nqw9utatMftGHVzOazIDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T22:52:30.968968Z","bundle_sha256":"f0e60c954cfb6380d69e9db83872c0cb8a8f0acfe8fbed87feaefd6d04a79836"}}