{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6LW74HMSDZEZPBVHJIJUMF4AEB","short_pith_number":"pith:6LW74HMS","schema_version":"1.0","canonical_sha256":"f2edfe1d921e499786a74a13461780206128263a762ccc48c6758799bf73299c","source":{"kind":"arxiv","id":"2505.06987","version":6},"attestation_state":"computed","paper":{"title":"Convert Language Model into a Value-based Strategic Planner","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Luo Ji, Qingqing Gu, Xiaokai Chen, Xiaoyu Wang, Yong Chen, Yue Zhao, Zhonglin Jiang","submitted_at":"2025-05-11T14:13:58Z","abstract_excerpt":"Emotional support conversation (ESC) aims to alleviate the emotional distress of individuals through effective conversations. Although large language models (LLMs) have obtained remarkable progress on ESC, most of these studies might not define the diagram from the state model perspective, therefore providing a suboptimal solution for long-term satisfaction. To address such an issue, we leverage the Q-learning on LLMs, and propose a framework called straQ*. Our framework allows a plug-and-play LLM to bootstrap the planning during ESC, determine the optimal strategy based on long-term returns, "},"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":"2505.06987","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-11T14:13:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9a2fde75db9a6bdb080067d2ea172445628d239a741ee5f2c3e0d49a31f756d4","abstract_canon_sha256":"9faf6391a35c4416695edc4bd2ae2d24951a4668e9f2c5ce9c59cfa712905874"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:00.998193Z","signature_b64":"MukqCBg8lBzwh+avH7jmJuRsRD5T1wyQIO/gojvLtvHrXZvnAjnAnMZ5dwC1JnliBPapophlxQFyXC2Q3asKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2edfe1d921e499786a74a13461780206128263a762ccc48c6758799bf73299c","last_reissued_at":"2026-07-05T12:00:00.997719Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:00.997719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convert Language Model into a Value-based Strategic Planner","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Luo Ji, Qingqing Gu, Xiaokai Chen, Xiaoyu Wang, Yong Chen, Yue Zhao, Zhonglin Jiang","submitted_at":"2025-05-11T14:13:58Z","abstract_excerpt":"Emotional support conversation (ESC) aims to alleviate the emotional distress of individuals through effective conversations. Although large language models (LLMs) have obtained remarkable progress on ESC, most of these studies might not define the diagram from the state model perspective, therefore providing a suboptimal solution for long-term satisfaction. To address such an issue, we leverage the Q-learning on LLMs, and propose a framework called straQ*. Our framework allows a plug-and-play LLM to bootstrap the planning during ESC, determine the optimal strategy based on long-term returns, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06987","kind":"arxiv","version":6},"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/2505.06987/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":"2505.06987","created_at":"2026-07-05T12:00:00.997777+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.06987v6","created_at":"2026-07-05T12:00:00.997777+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06987","created_at":"2026-07-05T12:00:00.997777+00:00"},{"alias_kind":"pith_short_12","alias_value":"6LW74HMSDZEZ","created_at":"2026-07-05T12:00:00.997777+00:00"},{"alias_kind":"pith_short_16","alias_value":"6LW74HMSDZEZPBVH","created_at":"2026-07-05T12:00:00.997777+00:00"},{"alias_kind":"pith_short_8","alias_value":"6LW74HMS","created_at":"2026-07-05T12:00:00.997777+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.12935","citing_title":"Towards Open-Ended Emotional Support Conversations in LLMs via Reinforcement Learning with Future-Oriented Rewards","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6LW74HMSDZEZPBVHJIJUMF4AEB","json":"https://pith.science/pith/6LW74HMSDZEZPBVHJIJUMF4AEB.json","graph_json":"https://pith.science/api/pith-number/6LW74HMSDZEZPBVHJIJUMF4AEB/graph.json","events_json":"https://pith.science/api/pith-number/6LW74HMSDZEZPBVHJIJUMF4AEB/events.json","paper":"https://pith.science/paper/6LW74HMS"},"agent_actions":{"view_html":"https://pith.science/pith/6LW74HMSDZEZPBVHJIJUMF4AEB","download_json":"https://pith.science/pith/6LW74HMSDZEZPBVHJIJUMF4AEB.json","view_paper":"https://pith.science/paper/6LW74HMS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.06987&json=true","fetch_graph":"https://pith.science/api/pith-number/6LW74HMSDZEZPBVHJIJUMF4AEB/graph.json","fetch_events":"https://pith.science/api/pith-number/6LW74HMSDZEZPBVHJIJUMF4AEB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6LW74HMSDZEZPBVHJIJUMF4AEB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6LW74HMSDZEZPBVHJIJUMF4AEB/action/storage_attestation","attest_author":"https://pith.science/pith/6LW74HMSDZEZPBVHJIJUMF4AEB/action/author_attestation","sign_citation":"https://pith.science/pith/6LW74HMSDZEZPBVHJIJUMF4AEB/action/citation_signature","submit_replication":"https://pith.science/pith/6LW74HMSDZEZPBVHJIJUMF4AEB/action/replication_record"}},"created_at":"2026-07-05T12:00:00.997777+00:00","updated_at":"2026-07-05T12:00:00.997777+00:00"}