{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:R5ER4KTK7OQDV2SHIPMRNA3V4B","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":"71f613f1b073458e606194d737d77ad0bc30cd8344569cec27b9405738026124","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T08:47:04Z","title_canon_sha256":"d1f57081c1960822e9bb5dca039fa16fd18667de4ad0679cb1ffec698f7f105a"},"schema_version":"1.0","source":{"id":"2411.19547","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19547","created_at":"2026-07-05T09:42:04Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19547v1","created_at":"2026-07-05T09:42:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19547","created_at":"2026-07-05T09:42:04Z"},{"alias_kind":"pith_short_12","alias_value":"R5ER4KTK7OQD","created_at":"2026-07-05T09:42:04Z"},{"alias_kind":"pith_short_16","alias_value":"R5ER4KTK7OQDV2SH","created_at":"2026-07-05T09:42:04Z"},{"alias_kind":"pith_short_8","alias_value":"R5ER4KTK","created_at":"2026-07-05T09:42:04Z"}],"graph_snapshots":[{"event_id":"sha256:a461cbbf50cecc29fde90c71eef2510dd191867071e473b508347e584b1b53ef","target":"graph","created_at":"2026-07-05T09:42:04Z","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/2411.19547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) offer a promising basis for creating agents that can tackle complex tasks through iterative environmental interaction. Existing methods either require these agents to mimic expert-provided trajectories or rely on definitive environmental feedback for reinforcement learning which limits their application to specific scenarios like gaming or code generation. This paper introduces a novel training method for LLM-based agents using weakly supervised signals from a critic LLM, bypassing the need for expert trajectories or definitive feedback. Our agents are trained in i","authors_text":"Dihong Gong, Meng Zhou, Pu Lu, Xiuqiang He, Zelong Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T08:47:04Z","title":"Training Agents with Weakly Supervised Feedback from Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19547","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:b6a91a238acc2f696f90a21180a7a22e9d2709d21b39cea04e38c83c0f519c0f","target":"record","created_at":"2026-07-05T09:42:04Z","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":"71f613f1b073458e606194d737d77ad0bc30cd8344569cec27b9405738026124","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T08:47:04Z","title_canon_sha256":"d1f57081c1960822e9bb5dca039fa16fd18667de4ad0679cb1ffec698f7f105a"},"schema_version":"1.0","source":{"id":"2411.19547","kind":"arxiv","version":1}},"canonical_sha256":"8f491e2a6afba03aea4743d9168375e060af541fd3c7505b1b3e0628c4657fb3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f491e2a6afba03aea4743d9168375e060af541fd3c7505b1b3e0628c4657fb3","first_computed_at":"2026-07-05T09:42:04.159045Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:04.159045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4JIAcE6gtp/ifiWHsvglCUmtFOYQo3Cpl3lBMiZG2eO5ELpTPoldVXTe7uN7ZNs2FGy73WAT3OckYxUbhUiRCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:04.159562Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.19547","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6a91a238acc2f696f90a21180a7a22e9d2709d21b39cea04e38c83c0f519c0f","sha256:a461cbbf50cecc29fde90c71eef2510dd191867071e473b508347e584b1b53ef"],"state_sha256":"72d3c03571c8f3d0e2db26c36ff45f48e760f4d04bd0c9e0a0de36b2d14704f6"}