{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ENZAIGGZJ4JTKBLKCYEFQFD366","short_pith_number":"pith:ENZAIGGZ","canonical_record":{"source":{"id":"2510.05592","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-10-07T05:32:44Z","cross_cats_sorted":["cs.CL","cs.LG","cs.MA"],"title_canon_sha256":"1cc56bf8f0f6c28689d899eed5955865f116316562a157e8796b09070b5ada26","abstract_canon_sha256":"82e9483b1af753c432322d61434add349d32bff2be4472819456e33e58d51cb3"},"schema_version":"1.0"},"canonical_sha256":"23720418d94f1335056a160858147bf7a9c34236b645bacc436093d577b8a443","source":{"kind":"arxiv","id":"2510.05592","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.05592","created_at":"2026-07-23T01:23:29Z"},{"alias_kind":"arxiv_version","alias_value":"2510.05592v2","created_at":"2026-07-23T01:23:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.05592","created_at":"2026-07-23T01:23:29Z"},{"alias_kind":"pith_short_12","alias_value":"ENZAIGGZJ4JT","created_at":"2026-07-23T01:23:29Z"},{"alias_kind":"pith_short_16","alias_value":"ENZAIGGZJ4JTKBLK","created_at":"2026-07-23T01:23:29Z"},{"alias_kind":"pith_short_8","alias_value":"ENZAIGGZ","created_at":"2026-07-23T01:23:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ENZAIGGZJ4JTKBLKCYEFQFD366","target":"record","payload":{"canonical_record":{"source":{"id":"2510.05592","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-10-07T05:32:44Z","cross_cats_sorted":["cs.CL","cs.LG","cs.MA"],"title_canon_sha256":"1cc56bf8f0f6c28689d899eed5955865f116316562a157e8796b09070b5ada26","abstract_canon_sha256":"82e9483b1af753c432322d61434add349d32bff2be4472819456e33e58d51cb3"},"schema_version":"1.0"},"canonical_sha256":"23720418d94f1335056a160858147bf7a9c34236b645bacc436093d577b8a443","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T01:23:29.429659Z","signature_b64":"ApVx4pqEFHuFOxZfygNRO7tCHvmYlBCLXHguhEYSefFTnqtQUlfVmnvvOBcwaXMAozHHHoWmPmLrAPeflncHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23720418d94f1335056a160858147bf7a9c34236b645bacc436093d577b8a443","last_reissued_at":"2026-07-23T01:23:29.428699Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T01:23:29.428699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.05592","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":"2026-07-23T01:23:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nDBLFAG9PybqcNVOhnb+vAOn5JphImbqMYbkk2vHd/3PpYvJ9RGblqPKnwNbjjAyRHCgr5lor/fcw3QHT2CgAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T03:39:18.422827Z"},"content_sha256":"99eb8349c6faad3cb962905aa5a28537da70843dca8171f53e91eb4dda681374","schema_version":"1.0","event_id":"sha256:99eb8349c6faad3cb962905aa5a28537da70843dca8171f53e91eb4dda681374"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ENZAIGGZJ4JTKBLKCYEFQFD366","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"In-the-Flow Agentic System Optimization for Effective Planning and Tool Use","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Haoxiang Zhang, James Zou, Jianwen Xie, Pan Lu, Seungju Han, Sheng Liu, Yejin Choi, Yu Zhang, Zhuofeng Li","submitted_at":"2025-10-07T05:32:44Z","abstract_excerpt":"Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this scales poorly with long horizons and diverse tools and generalizes weakly to new scenarios. Agentic systems offer a promising alternative by decomposing work across specialized modules, yet most remain training-free or rely on offline training decoupled from the live dynamics of multi-turn interaction. We introduce AgentFlow, a trainable, in-the-flow agentic fram"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.05592","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/2510.05592/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":"2026-07-23T01:23:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4/Dka5nsICe8KCnHOlpi+ld4Ri5dEPjXZIuYi0hGtffIaV/s+RjOyJ5kKXpiyVrhi0G7CveeILjWmaoXumpjBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T03:39:18.423205Z"},"content_sha256":"e9346f74e439bc7b194460e196dc3bbba1c54b38a8dcdf10f7b11c2577d61586","schema_version":"1.0","event_id":"sha256:e9346f74e439bc7b194460e196dc3bbba1c54b38a8dcdf10f7b11c2577d61586"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ENZAIGGZJ4JTKBLKCYEFQFD366/bundle.json","state_url":"https://pith.science/pith/ENZAIGGZJ4JTKBLKCYEFQFD366/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ENZAIGGZJ4JTKBLKCYEFQFD366/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":"2026-07-25T03:39:18Z","links":{"resolver":"https://pith.science/pith/ENZAIGGZJ4JTKBLKCYEFQFD366","bundle":"https://pith.science/pith/ENZAIGGZJ4JTKBLKCYEFQFD366/bundle.json","state":"https://pith.science/pith/ENZAIGGZJ4JTKBLKCYEFQFD366/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ENZAIGGZJ4JTKBLKCYEFQFD366/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ENZAIGGZJ4JTKBLKCYEFQFD366","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":"82e9483b1af753c432322d61434add349d32bff2be4472819456e33e58d51cb3","cross_cats_sorted":["cs.CL","cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-10-07T05:32:44Z","title_canon_sha256":"1cc56bf8f0f6c28689d899eed5955865f116316562a157e8796b09070b5ada26"},"schema_version":"1.0","source":{"id":"2510.05592","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.05592","created_at":"2026-07-23T01:23:29Z"},{"alias_kind":"arxiv_version","alias_value":"2510.05592v2","created_at":"2026-07-23T01:23:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.05592","created_at":"2026-07-23T01:23:29Z"},{"alias_kind":"pith_short_12","alias_value":"ENZAIGGZJ4JT","created_at":"2026-07-23T01:23:29Z"},{"alias_kind":"pith_short_16","alias_value":"ENZAIGGZJ4JTKBLK","created_at":"2026-07-23T01:23:29Z"},{"alias_kind":"pith_short_8","alias_value":"ENZAIGGZ","created_at":"2026-07-23T01:23:29Z"}],"graph_snapshots":[{"event_id":"sha256:e9346f74e439bc7b194460e196dc3bbba1c54b38a8dcdf10f7b11c2577d61586","target":"graph","created_at":"2026-07-23T01:23:29Z","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/2510.05592/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this scales poorly with long horizons and diverse tools and generalizes weakly to new scenarios. Agentic systems offer a promising alternative by decomposing work across specialized modules, yet most remain training-free or rely on offline training decoupled from the live dynamics of multi-turn interaction. We introduce AgentFlow, a trainable, in-the-flow agentic fram","authors_text":"Haoxiang Zhang, James Zou, Jianwen Xie, Pan Lu, Seungju Han, Sheng Liu, Yejin Choi, Yu Zhang, Zhuofeng Li","cross_cats":["cs.CL","cs.LG","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-10-07T05:32:44Z","title":"In-the-Flow Agentic System Optimization for Effective Planning and Tool Use"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.05592","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":"sha256:99eb8349c6faad3cb962905aa5a28537da70843dca8171f53e91eb4dda681374","target":"record","created_at":"2026-07-23T01:23:29Z","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":"82e9483b1af753c432322d61434add349d32bff2be4472819456e33e58d51cb3","cross_cats_sorted":["cs.CL","cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-10-07T05:32:44Z","title_canon_sha256":"1cc56bf8f0f6c28689d899eed5955865f116316562a157e8796b09070b5ada26"},"schema_version":"1.0","source":{"id":"2510.05592","kind":"arxiv","version":2}},"canonical_sha256":"23720418d94f1335056a160858147bf7a9c34236b645bacc436093d577b8a443","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23720418d94f1335056a160858147bf7a9c34236b645bacc436093d577b8a443","first_computed_at":"2026-07-23T01:23:29.428699Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-23T01:23:29.428699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ApVx4pqEFHuFOxZfygNRO7tCHvmYlBCLXHguhEYSefFTnqtQUlfVmnvvOBcwaXMAozHHHoWmPmLrAPeflncHDg==","signature_status":"signed_v1","signed_at":"2026-07-23T01:23:29.429659Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.05592","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99eb8349c6faad3cb962905aa5a28537da70843dca8171f53e91eb4dda681374","sha256:e9346f74e439bc7b194460e196dc3bbba1c54b38a8dcdf10f7b11c2577d61586"],"state_sha256":"058cbeb08bc4f9767ad4f51db316ad4e13228bdc0e074539e8e73ee619c3b9e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZoJTpTeJKMSFhXCywt/mPCquRd7ySsgrTSl1VlR95BGAONBI/BexM05caqVFOOU1rlT+lwcI1kdfjCCgDg5/Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-25T03:39:18.425500Z","bundle_sha256":"4357534c2517344f46a1da790ed4a92e44714c89c015ac670be7c8fa080a7cf1"}}