{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TLTBTR2TWV45IMG3IF5PDVRYXO","short_pith_number":"pith:TLTBTR2T","schema_version":"1.0","canonical_sha256":"9ae619c753b579d430db417af1d638bb94b685e2280eb6ecf48bd0ddc854dbbf","source":{"kind":"arxiv","id":"2402.01737","version":3},"attestation_state":"computed","paper":{"title":"Assistive Large Language Model Agents for Socially-Aware Negotiation Dialogues","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gholamreza Haffari, Lizhen Qu, Yuncheng Hua","submitted_at":"2024-01-29T09:07:40Z","abstract_excerpt":"We develop assistive agents based on Large Language Models (LLMs) that aid interlocutors in business negotiations. Specifically, we simulate business negotiations by letting two LLM-based agents engage in role play. A third LLM acts as a remediator agent to rewrite utterances violating norms for improving negotiation outcomes. We introduce a simple tuning-free and label-free In-Context Learning (ICL) method to identify high-quality ICL exemplars for the remediator, where we propose a novel select criteria, called value impact, to measure the quality of the negotiation outcomes. We provide rich"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2402.01737","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-29T09:07:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"408d8c796cfd48154167f6c651518eacc74b031d3cee09de538a09dcc00a341a","abstract_canon_sha256":"04236f4b972c3427e268ac0fa94c7f6a738e9e176db733ccf65f4bd7bd030abd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:15.409371Z","signature_b64":"3x5hHCciOz+CQiL4//nAEDmNSrkJNOwNRgloYP+rK9vlj9j7mZpBCysPjCw6jQJ3PEah3Bd+fDtwdsCPFS+8Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ae619c753b579d430db417af1d638bb94b685e2280eb6ecf48bd0ddc854dbbf","last_reissued_at":"2026-07-05T10:15:15.408874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:15.408874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assistive Large Language Model Agents for Socially-Aware Negotiation Dialogues","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gholamreza Haffari, Lizhen Qu, Yuncheng Hua","submitted_at":"2024-01-29T09:07:40Z","abstract_excerpt":"We develop assistive agents based on Large Language Models (LLMs) that aid interlocutors in business negotiations. Specifically, we simulate business negotiations by letting two LLM-based agents engage in role play. A third LLM acts as a remediator agent to rewrite utterances violating norms for improving negotiation outcomes. We introduce a simple tuning-free and label-free In-Context Learning (ICL) method to identify high-quality ICL exemplars for the remediator, where we propose a novel select criteria, called value impact, to measure the quality of the negotiation outcomes. We provide rich"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01737","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/2402.01737/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.01737","created_at":"2026-07-05T10:15:15.408933+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01737v3","created_at":"2026-07-05T10:15:15.408933+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01737","created_at":"2026-07-05T10:15:15.408933+00:00"},{"alias_kind":"pith_short_12","alias_value":"TLTBTR2TWV45","created_at":"2026-07-05T10:15:15.408933+00:00"},{"alias_kind":"pith_short_16","alias_value":"TLTBTR2TWV45IMG3","created_at":"2026-07-05T10:15:15.408933+00:00"},{"alias_kind":"pith_short_8","alias_value":"TLTBTR2T","created_at":"2026-07-05T10:15:15.408933+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11379","citing_title":"Automated Mediator for Human Negotiation: Pre-Mediation via a Structured LLM Pipeline","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TLTBTR2TWV45IMG3IF5PDVRYXO","json":"https://pith.science/pith/TLTBTR2TWV45IMG3IF5PDVRYXO.json","graph_json":"https://pith.science/api/pith-number/TLTBTR2TWV45IMG3IF5PDVRYXO/graph.json","events_json":"https://pith.science/api/pith-number/TLTBTR2TWV45IMG3IF5PDVRYXO/events.json","paper":"https://pith.science/paper/TLTBTR2T"},"agent_actions":{"view_html":"https://pith.science/pith/TLTBTR2TWV45IMG3IF5PDVRYXO","download_json":"https://pith.science/pith/TLTBTR2TWV45IMG3IF5PDVRYXO.json","view_paper":"https://pith.science/paper/TLTBTR2T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01737&json=true","fetch_graph":"https://pith.science/api/pith-number/TLTBTR2TWV45IMG3IF5PDVRYXO/graph.json","fetch_events":"https://pith.science/api/pith-number/TLTBTR2TWV45IMG3IF5PDVRYXO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TLTBTR2TWV45IMG3IF5PDVRYXO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TLTBTR2TWV45IMG3IF5PDVRYXO/action/storage_attestation","attest_author":"https://pith.science/pith/TLTBTR2TWV45IMG3IF5PDVRYXO/action/author_attestation","sign_citation":"https://pith.science/pith/TLTBTR2TWV45IMG3IF5PDVRYXO/action/citation_signature","submit_replication":"https://pith.science/pith/TLTBTR2TWV45IMG3IF5PDVRYXO/action/replication_record"}},"created_at":"2026-07-05T10:15:15.408933+00:00","updated_at":"2026-07-05T10:15:15.408933+00:00"}