{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:D3HMHTAINQNELCH7AT3BRODNTF","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":"40f8afb223dacde3ffd310ed67ebff42446a321951855fe47cd35dca04b92732","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-02T02:18:14Z","title_canon_sha256":"bc8573cefdece7b13d649a3ccc0c422df6ccfa8fff00c5d91d9b0c5fe2f45a05"},"schema_version":"1.0","source":{"id":"2407.01887","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01887","created_at":"2026-07-05T11:18:13Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01887v4","created_at":"2026-07-05T11:18:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01887","created_at":"2026-07-05T11:18:13Z"},{"alias_kind":"pith_short_12","alias_value":"D3HMHTAINQNE","created_at":"2026-07-05T11:18:13Z"},{"alias_kind":"pith_short_16","alias_value":"D3HMHTAINQNELCH7","created_at":"2026-07-05T11:18:13Z"},{"alias_kind":"pith_short_8","alias_value":"D3HMHTAI","created_at":"2026-07-05T11:18:13Z"}],"graph_snapshots":[{"event_id":"sha256:2c7709b738e4ef4a4d59377c2c0c851ccb6312477a12c23405a50d5cefde780d","target":"graph","created_at":"2026-07-05T11:18:13Z","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/2407.01887/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In-Context Reinforcement Learning (ICRL) is a frontier paradigm to solve Reinforcement Learning (RL) problems in the foundation model era. While ICRL capabilities have been demonstrated in transformers through task-specific training, the potential of Large Language Models (LLMs) out-of-the-box remains largely unexplored. This paper investigates whether LLMs can generalize cross-domain to perform ICRL under the problem of Dueling Bandits (DB), a stateless preference-based RL setting. We find that the top-performing LLMs exhibit a notable zero-shot capacity for relative decision-making, which tr","authors_text":"Fanzeng Xia, Hao Liu, Tongxin Li, Yisong Yue","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-02T02:18:14Z","title":"Beyond Numeric Rewards: In-Context Dueling Bandits with LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01887","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":"sha256:09ee9fccdfc6c3e472c0644ec6471019bfad42698615ea6ecfebd6b9a2242b1e","target":"record","created_at":"2026-07-05T11:18:13Z","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":"40f8afb223dacde3ffd310ed67ebff42446a321951855fe47cd35dca04b92732","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-02T02:18:14Z","title_canon_sha256":"bc8573cefdece7b13d649a3ccc0c422df6ccfa8fff00c5d91d9b0c5fe2f45a05"},"schema_version":"1.0","source":{"id":"2407.01887","kind":"arxiv","version":4}},"canonical_sha256":"1ecec3cc086c1a4588ff04f618b86d99404ee26942073a25389dfc1c67d14a31","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ecec3cc086c1a4588ff04f618b86d99404ee26942073a25389dfc1c67d14a31","first_computed_at":"2026-07-05T11:18:13.128119Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:13.128119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aV7apiAYW+Zi/Latf8+cRoSfGt7xkXFO5rpmU2/4w/qVfUQ+K1U7f8LmbDkrMw+KBfzS0AtgEcSUtrUk5XLjAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:13.128584Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.01887","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09ee9fccdfc6c3e472c0644ec6471019bfad42698615ea6ecfebd6b9a2242b1e","sha256:2c7709b738e4ef4a4d59377c2c0c851ccb6312477a12c23405a50d5cefde780d"],"state_sha256":"4af377010fda5b8ec3a6cbdb8006bf539a53956b3005452e4cdb81e6939e424a"}