{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BIZZE6X62F5KPCB4GC5O45VPMN","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":"6905b11b5057fec3417cd2430af132bad56b10c4168e432a5b03fa6b522089d8","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T17:57:47Z","title_canon_sha256":"d84fe8257488474a432ba7ea656b6c8e341cb22802f398712423a4b11485875f"},"schema_version":"1.0","source":{"id":"2404.15269","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.15269","created_at":"2026-07-05T09:39:22Z"},{"alias_kind":"arxiv_version","alias_value":"2404.15269v3","created_at":"2026-07-05T09:39:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15269","created_at":"2026-07-05T09:39:22Z"},{"alias_kind":"pith_short_12","alias_value":"BIZZE6X62F5K","created_at":"2026-07-05T09:39:22Z"},{"alias_kind":"pith_short_16","alias_value":"BIZZE6X62F5KPCB4","created_at":"2026-07-05T09:39:22Z"},{"alias_kind":"pith_short_8","alias_value":"BIZZE6X6","created_at":"2026-07-05T09:39:22Z"}],"graph_snapshots":[{"event_id":"sha256:c3720a7944d3cc1baf8a938f3695a3a58ee4e17cea2d0c27aa573815be466323","target":"graph","created_at":"2026-07-05T09:39:22Z","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/2404.15269/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study interactive learning of LLM-based language agents based on user edits made to the agent's output. In a typical setting such as writing assistants, the user interacts with a language agent to generate a response given a context, and may optionally edit the agent response to personalize it based on their latent preference, in addition to improving the correctness. The edit feedback is naturally generated, making it a suitable candidate for improving the agent's alignment with the user's preference, and for reducing the cost of user edits over time. We propose a learning framework, PRELU","authors_text":"Alexey Taymanov, Dipendra Misra, Eduardo Salinas, Ge Gao, Paul Mineiro","cross_cats":["cs.AI","cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T17:57:47Z","title":"Aligning LLM Agents by Learning Latent Preference from User Edits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15269","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":"sha256:1471f630b8ef87498bc591c12ef82001c87bd06539f38816be062a92dc357898","target":"record","created_at":"2026-07-05T09:39:22Z","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":"6905b11b5057fec3417cd2430af132bad56b10c4168e432a5b03fa6b522089d8","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T17:57:47Z","title_canon_sha256":"d84fe8257488474a432ba7ea656b6c8e341cb22802f398712423a4b11485875f"},"schema_version":"1.0","source":{"id":"2404.15269","kind":"arxiv","version":3}},"canonical_sha256":"0a33927afed17aa7883c30baee76af634df626679773c811f734befde0e02322","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a33927afed17aa7883c30baee76af634df626679773c811f734befde0e02322","first_computed_at":"2026-07-05T09:39:22.705947Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:39:22.705947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W0iyNPIAMx1YSrQyQZSEAxk+TLL3Ep1VT2OzmRLl2lGreieg1e6S8FXLZDCLwilyuEc8TZBVlYh/1VtPhHZxCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:39:22.706472Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.15269","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1471f630b8ef87498bc591c12ef82001c87bd06539f38816be062a92dc357898","sha256:c3720a7944d3cc1baf8a938f3695a3a58ee4e17cea2d0c27aa573815be466323"],"state_sha256":"9d7020f41eeb0d6dba7071aa0dca26631d742a4cecba225c3770b0783e534fe0"}