{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JQWN5B35FAZ3KNFBSY7OAFKQXL","short_pith_number":"pith:JQWN5B35","canonical_record":{"source":{"id":"2310.01444","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-01T07:50:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bcf63e9c66ca4622ee1f71ac551850ff039230622d10c5e003971c4645e035c0","abstract_canon_sha256":"0d4f21c539bc06636fcca09d7845ee43927bf51339d1a786e3c1c9d1b7481d1b"},"schema_version":"1.0"},"canonical_sha256":"4c2cde877d2833b534a1963ee01550bad09023ca58e5d829d02d7fdcb4a4bce8","source":{"kind":"arxiv","id":"2310.01444","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.01444","created_at":"2026-07-05T08:07:29Z"},{"alias_kind":"arxiv_version","alias_value":"2310.01444v3","created_at":"2026-07-05T08:07:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01444","created_at":"2026-07-05T08:07:29Z"},{"alias_kind":"pith_short_12","alias_value":"JQWN5B35FAZ3","created_at":"2026-07-05T08:07:29Z"},{"alias_kind":"pith_short_16","alias_value":"JQWN5B35FAZ3KNFB","created_at":"2026-07-05T08:07:29Z"},{"alias_kind":"pith_short_8","alias_value":"JQWN5B35","created_at":"2026-07-05T08:07:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JQWN5B35FAZ3KNFBSY7OAFKQXL","target":"record","payload":{"canonical_record":{"source":{"id":"2310.01444","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-01T07:50:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bcf63e9c66ca4622ee1f71ac551850ff039230622d10c5e003971c4645e035c0","abstract_canon_sha256":"0d4f21c539bc06636fcca09d7845ee43927bf51339d1a786e3c1c9d1b7481d1b"},"schema_version":"1.0"},"canonical_sha256":"4c2cde877d2833b534a1963ee01550bad09023ca58e5d829d02d7fdcb4a4bce8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:29.697510Z","signature_b64":"2PHf/cvvfc9lQhXL9xnkeyjXizhBZSzDD+aG1ZCou/XXJ6AkSsBalcf1rIEa5ScXdM1oz+dRaYwpLZAWXCC4Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c2cde877d2833b534a1963ee01550bad09023ca58e5d829d02d7fdcb4a4bce8","last_reissued_at":"2026-07-05T08:07:29.697027Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:29.697027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.01444","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":"2026-07-05T08:07:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tQCE1wtm9FEmRpgEvIwLn2dc0n8PxvgsBYP3K/oVkdyu5JHy8qrGJe5Gr/EUvW0g5MeEQuQqb90YvlP4CigjAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T23:52:49.377814Z"},"content_sha256":"0dd7ec167b7b9741a893d68762c8c0333823789f7d517d1e998804c675540260","schema_version":"1.0","event_id":"sha256:0dd7ec167b7b9741a893d68762c8c0333823789f7d517d1e998804c675540260"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JQWN5B35FAZ3KNFBSY7OAFKQXL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adapting LLM Agents with Universal Feedback in Communication","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chao Zhang, Kuan Wang, Michael Santacroce, Yadong Lu, Yelong Shen, Yeyun Gong","submitted_at":"2023-10-01T07:50:30Z","abstract_excerpt":"Recent advances in large language models (LLMs) have demonstrated potential for LLM agents. To facilitate the training for these agents with both linguistic feedback and non-linguistic reward signals, we introduce Learning through Communication (LTC). We design a universal buffer to store all the feedback, and an iterative pipeline to enable an LLM agent to explore and update its policy in an given environment. To optimize agent interactions for task-specific learning with our universal buffer and pipeline, we introduce diverse communication patterns tailored for both single-agent and multi-ag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01444","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/2310.01444/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":"2026-07-05T08:07:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nIpP/vlusLHu8VODcibjcjXHUOy9NbHFq3kYYsxw0iW+KvFk35Z40j6+uIa+I98Cc3yPTbnwsog9FsTcdzj/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T23:52:49.378827Z"},"content_sha256":"264dd6ffb7f7eaf927016af568a0db7728bc5c55b10245f7ffc4a3251ca50e82","schema_version":"1.0","event_id":"sha256:264dd6ffb7f7eaf927016af568a0db7728bc5c55b10245f7ffc4a3251ca50e82"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JQWN5B35FAZ3KNFBSY7OAFKQXL/bundle.json","state_url":"https://pith.science/pith/JQWN5B35FAZ3KNFBSY7OAFKQXL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JQWN5B35FAZ3KNFBSY7OAFKQXL/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":"2026-08-12T23:52:49Z","links":{"resolver":"https://pith.science/pith/JQWN5B35FAZ3KNFBSY7OAFKQXL","bundle":"https://pith.science/pith/JQWN5B35FAZ3KNFBSY7OAFKQXL/bundle.json","state":"https://pith.science/pith/JQWN5B35FAZ3KNFBSY7OAFKQXL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JQWN5B35FAZ3KNFBSY7OAFKQXL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JQWN5B35FAZ3KNFBSY7OAFKQXL","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":"0d4f21c539bc06636fcca09d7845ee43927bf51339d1a786e3c1c9d1b7481d1b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-01T07:50:30Z","title_canon_sha256":"bcf63e9c66ca4622ee1f71ac551850ff039230622d10c5e003971c4645e035c0"},"schema_version":"1.0","source":{"id":"2310.01444","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.01444","created_at":"2026-07-05T08:07:29Z"},{"alias_kind":"arxiv_version","alias_value":"2310.01444v3","created_at":"2026-07-05T08:07:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01444","created_at":"2026-07-05T08:07:29Z"},{"alias_kind":"pith_short_12","alias_value":"JQWN5B35FAZ3","created_at":"2026-07-05T08:07:29Z"},{"alias_kind":"pith_short_16","alias_value":"JQWN5B35FAZ3KNFB","created_at":"2026-07-05T08:07:29Z"},{"alias_kind":"pith_short_8","alias_value":"JQWN5B35","created_at":"2026-07-05T08:07:29Z"}],"graph_snapshots":[{"event_id":"sha256:264dd6ffb7f7eaf927016af568a0db7728bc5c55b10245f7ffc4a3251ca50e82","target":"graph","created_at":"2026-07-05T08:07:29Z","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/2310.01444/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large language models (LLMs) have demonstrated potential for LLM agents. To facilitate the training for these agents with both linguistic feedback and non-linguistic reward signals, we introduce Learning through Communication (LTC). We design a universal buffer to store all the feedback, and an iterative pipeline to enable an LLM agent to explore and update its policy in an given environment. To optimize agent interactions for task-specific learning with our universal buffer and pipeline, we introduce diverse communication patterns tailored for both single-agent and multi-ag","authors_text":"Chao Zhang, Kuan Wang, Michael Santacroce, Yadong Lu, Yelong Shen, Yeyun Gong","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-01T07:50:30Z","title":"Adapting LLM Agents with Universal Feedback in Communication"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01444","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":"sha256:0dd7ec167b7b9741a893d68762c8c0333823789f7d517d1e998804c675540260","target":"record","created_at":"2026-07-05T08:07:29Z","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":"0d4f21c539bc06636fcca09d7845ee43927bf51339d1a786e3c1c9d1b7481d1b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-01T07:50:30Z","title_canon_sha256":"bcf63e9c66ca4622ee1f71ac551850ff039230622d10c5e003971c4645e035c0"},"schema_version":"1.0","source":{"id":"2310.01444","kind":"arxiv","version":3}},"canonical_sha256":"4c2cde877d2833b534a1963ee01550bad09023ca58e5d829d02d7fdcb4a4bce8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c2cde877d2833b534a1963ee01550bad09023ca58e5d829d02d7fdcb4a4bce8","first_computed_at":"2026-07-05T08:07:29.697027Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:07:29.697027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2PHf/cvvfc9lQhXL9xnkeyjXizhBZSzDD+aG1ZCou/XXJ6AkSsBalcf1rIEa5ScXdM1oz+dRaYwpLZAWXCC4Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:07:29.697510Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.01444","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0dd7ec167b7b9741a893d68762c8c0333823789f7d517d1e998804c675540260","sha256:264dd6ffb7f7eaf927016af568a0db7728bc5c55b10245f7ffc4a3251ca50e82"],"state_sha256":"51ef0abded58e761c20fabb7e3bd1d433ef876b757b7da420e60a260fd4d9168"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NCqusXn4BSQj+jP9SfF8KAF3j53IrhfJymxJL3XMhxDZGnhENW+7/7df268+Ja3NDUXnsYH+E/UwTmkV5WN0Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T23:52:49.388504Z","bundle_sha256":"ee66692f2d427eac0f85f9001e2951be18ed9029191bd667021e1408f3573a58"}}