{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:35TESAL5TZYZIKB2746EZ72Q62","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":"69ed2284114fc30edc7b2c559b60029ec3b95cedaf2a6a3f2cc622a5fe2b2637","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-29T09:02:57Z","title_canon_sha256":"4f484f353352a7426b02b4caf8ac92c67bcf7ba7d88cfac8c1f231ce9d5c29d6"},"schema_version":"1.0","source":{"id":"2310.18940","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.18940","created_at":"2026-07-05T11:11:30Z"},{"alias_kind":"arxiv_version","alias_value":"2310.18940v4","created_at":"2026-07-05T11:11:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18940","created_at":"2026-07-05T11:11:30Z"},{"alias_kind":"pith_short_12","alias_value":"35TESAL5TZYZ","created_at":"2026-07-05T11:11:30Z"},{"alias_kind":"pith_short_16","alias_value":"35TESAL5TZYZIKB2","created_at":"2026-07-05T11:11:30Z"},{"alias_kind":"pith_short_8","alias_value":"35TESAL5","created_at":"2026-07-05T11:11:30Z"}],"graph_snapshots":[{"event_id":"sha256:af550d7704c9a4e6e5f6301df7381b9db462a0c898e04eac602f6d887e989979","target":"graph","created_at":"2026-07-05T11:11:30Z","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/2310.18940/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agents built with large language models (LLMs) have shown great potential across a wide range of domains. However, in complex decision-making tasks, pure LLM-based agents tend to exhibit intrinsic bias in their choice of actions, which is inherited from the model's training data and results in suboptimal performance. To develop strategic language agents, i.e., agents that generate flexible language actions and possess strong decision-making abilities, we propose a novel framework that powers LLM-based agents with reinforcement learning (RL). We consider Werewolf, a popular social deduction gam","authors_text":"Chao Yu, Fei Fang, Yi Wu, Yu Wang, Zelai Xu","cross_cats":["cs.LG","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-29T09:02:57Z","title":"Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18940","kind":"arxiv","version":4},"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":"sha256:543af93c880f0ccac66e002947fe5dd296595af7faa9d7348da041dc867053cf","target":"record","created_at":"2026-07-05T11:11:30Z","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":"69ed2284114fc30edc7b2c559b60029ec3b95cedaf2a6a3f2cc622a5fe2b2637","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-29T09:02:57Z","title_canon_sha256":"4f484f353352a7426b02b4caf8ac92c67bcf7ba7d88cfac8c1f231ce9d5c29d6"},"schema_version":"1.0","source":{"id":"2310.18940","kind":"arxiv","version":4}},"canonical_sha256":"df6649017d9e7194283aff3c4cff50f6a817a297a01344e01f002b7c53a8b136","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df6649017d9e7194283aff3c4cff50f6a817a297a01344e01f002b7c53a8b136","first_computed_at":"2026-07-05T11:11:30.424929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:30.424929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/b3qiBCQvBkJFDltxxDk+4vsUv6CL5hW5idOy/ju/v/6S7UZSPVREk6PnbquncdNayNjEdVDKGfQHbk9ujiCBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:30.425473Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.18940","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:543af93c880f0ccac66e002947fe5dd296595af7faa9d7348da041dc867053cf","sha256:af550d7704c9a4e6e5f6301df7381b9db462a0c898e04eac602f6d887e989979"],"state_sha256":"b689b123d57fb8367fdc03db3ebb748e2fd8623ae8c6dae12bc93aa2c29a1835"}