{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LASXUZBYBB47U4UXO4TH327C3H","short_pith_number":"pith:LASXUZBY","canonical_record":{"source":{"id":"2406.11176","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T03:29:13Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"320ded1f74e384bb2eb8a7957228ecc69b270e3cb930e1f79a97b6c42afe61ef","abstract_canon_sha256":"3a8b19f145027514fc1cfe5e484e1876ccb45ce352fc6f68b65766c2e7065504"},"schema_version":"1.0"},"canonical_sha256":"58257a64380879fa729777267debe2d9e5e11bf417c11fcc1e389e75e431cdee","source":{"kind":"arxiv","id":"2406.11176","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11176","created_at":"2026-07-05T09:11:26Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11176v2","created_at":"2026-07-05T09:11:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11176","created_at":"2026-07-05T09:11:26Z"},{"alias_kind":"pith_short_12","alias_value":"LASXUZBYBB47","created_at":"2026-07-05T09:11:26Z"},{"alias_kind":"pith_short_16","alias_value":"LASXUZBYBB47U4UX","created_at":"2026-07-05T09:11:26Z"},{"alias_kind":"pith_short_8","alias_value":"LASXUZBY","created_at":"2026-07-05T09:11:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LASXUZBYBB47U4UXO4TH327C3H","target":"record","payload":{"canonical_record":{"source":{"id":"2406.11176","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T03:29:13Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"320ded1f74e384bb2eb8a7957228ecc69b270e3cb930e1f79a97b6c42afe61ef","abstract_canon_sha256":"3a8b19f145027514fc1cfe5e484e1876ccb45ce352fc6f68b65766c2e7065504"},"schema_version":"1.0"},"canonical_sha256":"58257a64380879fa729777267debe2d9e5e11bf417c11fcc1e389e75e431cdee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:26.890014Z","signature_b64":"CSsHzjTHzdFCIDLHp01nP4K7EyIAjy4ajChzmPJ3IEfHIBO32I6q3+LFebxY61CLBoWU/vrTDxoWIo5PSurtDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58257a64380879fa729777267debe2d9e5e11bf417c11fcc1e389e75e431cdee","last_reissued_at":"2026-07-05T09:11:26.889463Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:26.889463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.11176","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:11:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"piT2tiTi7kUHin8BDm5WkBz6u9InYsjlr/Cx64zMKl+JgnLpPExFezppDpm2BUk+Rh/MfR6UcpP54C4Uiz5PDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:05:01.784994Z"},"content_sha256":"a5e46c06293d41510dd374e376baa9ec16d81fa5e32b8cae15d3d6ebf35a6470","schema_version":"1.0","event_id":"sha256:a5e46c06293d41510dd374e376baa9ec16d81fa5e32b8cae15d3d6ebf35a6470"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LASXUZBYBB47U4UXO4TH327C3H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Cheng Li, Ke Wang, Sujian Li, Weimin Xiong, Wei Peng, Wenhao Wu, Xiutian Zhao, Xun Wang, Yifan Song","submitted_at":"2024-06-17T03:29:13Z","abstract_excerpt":"Large language model agents have exhibited exceptional performance across a range of complex interactive tasks. Recent approaches have utilized tuning with expert trajectories to enhance agent performance, yet they primarily concentrate on outcome rewards, which may lead to errors or suboptimal actions due to the absence of process supervision signals. In this paper, we introduce the Iterative step-level Process Refinement (IPR) framework, which provides detailed step-by-step guidance to enhance agent training. Specifically, we adopt the Monte Carlo method to estimate step-level rewards. Durin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11176","kind":"arxiv","version":2},"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/2406.11176/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":"2026-07-05T09:11:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zmS0l5l/eeCWy/b4Ad8VOjbeB1K65jAmUkOLr+pfHxhDAyOkOwo3+fFw+tk6l9UvAQ74DrGs0CqUSJUWUJlDCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:05:01.785526Z"},"content_sha256":"78b4f8a2acba41bcc4d21181d8ccc469d40dfd082fa64403e64cdebab6065ded","schema_version":"1.0","event_id":"sha256:78b4f8a2acba41bcc4d21181d8ccc469d40dfd082fa64403e64cdebab6065ded"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LASXUZBYBB47U4UXO4TH327C3H/bundle.json","state_url":"https://pith.science/pith/LASXUZBYBB47U4UXO4TH327C3H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LASXUZBYBB47U4UXO4TH327C3H/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":"2026-08-07T18:05:01Z","links":{"resolver":"https://pith.science/pith/LASXUZBYBB47U4UXO4TH327C3H","bundle":"https://pith.science/pith/LASXUZBYBB47U4UXO4TH327C3H/bundle.json","state":"https://pith.science/pith/LASXUZBYBB47U4UXO4TH327C3H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LASXUZBYBB47U4UXO4TH327C3H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LASXUZBYBB47U4UXO4TH327C3H","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":"3a8b19f145027514fc1cfe5e484e1876ccb45ce352fc6f68b65766c2e7065504","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T03:29:13Z","title_canon_sha256":"320ded1f74e384bb2eb8a7957228ecc69b270e3cb930e1f79a97b6c42afe61ef"},"schema_version":"1.0","source":{"id":"2406.11176","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11176","created_at":"2026-07-05T09:11:26Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11176v2","created_at":"2026-07-05T09:11:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11176","created_at":"2026-07-05T09:11:26Z"},{"alias_kind":"pith_short_12","alias_value":"LASXUZBYBB47","created_at":"2026-07-05T09:11:26Z"},{"alias_kind":"pith_short_16","alias_value":"LASXUZBYBB47U4UX","created_at":"2026-07-05T09:11:26Z"},{"alias_kind":"pith_short_8","alias_value":"LASXUZBY","created_at":"2026-07-05T09:11:26Z"}],"graph_snapshots":[{"event_id":"sha256:78b4f8a2acba41bcc4d21181d8ccc469d40dfd082fa64403e64cdebab6065ded","target":"graph","created_at":"2026-07-05T09:11:26Z","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/2406.11176/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model agents have exhibited exceptional performance across a range of complex interactive tasks. Recent approaches have utilized tuning with expert trajectories to enhance agent performance, yet they primarily concentrate on outcome rewards, which may lead to errors or suboptimal actions due to the absence of process supervision signals. In this paper, we introduce the Iterative step-level Process Refinement (IPR) framework, which provides detailed step-by-step guidance to enhance agent training. Specifically, we adopt the Monte Carlo method to estimate step-level rewards. Durin","authors_text":"Cheng Li, Ke Wang, Sujian Li, Weimin Xiong, Wei Peng, Wenhao Wu, Xiutian Zhao, Xun Wang, Yifan Song","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T03:29:13Z","title":"Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11176","kind":"arxiv","version":2},"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:a5e46c06293d41510dd374e376baa9ec16d81fa5e32b8cae15d3d6ebf35a6470","target":"record","created_at":"2026-07-05T09:11:26Z","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":"3a8b19f145027514fc1cfe5e484e1876ccb45ce352fc6f68b65766c2e7065504","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T03:29:13Z","title_canon_sha256":"320ded1f74e384bb2eb8a7957228ecc69b270e3cb930e1f79a97b6c42afe61ef"},"schema_version":"1.0","source":{"id":"2406.11176","kind":"arxiv","version":2}},"canonical_sha256":"58257a64380879fa729777267debe2d9e5e11bf417c11fcc1e389e75e431cdee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58257a64380879fa729777267debe2d9e5e11bf417c11fcc1e389e75e431cdee","first_computed_at":"2026-07-05T09:11:26.889463Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:11:26.889463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CSsHzjTHzdFCIDLHp01nP4K7EyIAjy4ajChzmPJ3IEfHIBO32I6q3+LFebxY61CLBoWU/vrTDxoWIo5PSurtDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:11:26.890014Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11176","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5e46c06293d41510dd374e376baa9ec16d81fa5e32b8cae15d3d6ebf35a6470","sha256:78b4f8a2acba41bcc4d21181d8ccc469d40dfd082fa64403e64cdebab6065ded"],"state_sha256":"c22b655ed2825c020603c5042a2d78287c010fa4f78234b54478fbb20eaae4b4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mF6dMilH4Obj9i2YLcX1tqKAfuM0wGljDevmLESQgmqUtfZKwur4bkHGolB0sYpRFldSLfdBzjTN1LgYoK6WDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:05:01.791319Z","bundle_sha256":"e580c423d2ad56725a151c85f6584040c9225692f1c884a5eb354d266ff80d85"}}