{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WOIQ2GHI467TQQK3IYSS6HHEOL","short_pith_number":"pith:WOIQ2GHI","schema_version":"1.0","canonical_sha256":"b3910d18e8e7bf38415b46252f1ce472ec8e31072ff18355f788cee5e714ac30","source":{"kind":"arxiv","id":"2402.12621","version":2},"attestation_state":"computed","paper":{"title":"Reflect-RL: Two-Player Online RL Fine-Tuning for LMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Beibin Li, Runlong Zhou, Simon S. Du","submitted_at":"2024-02-20T01:04:21Z","abstract_excerpt":"As language models (LMs) demonstrate their capabilities in various fields, their application to tasks requiring multi-round interactions has become increasingly popular. These tasks usually have complex dynamics, so supervised fine-tuning (SFT) on a limited offline dataset does not yield good performance. However, only a few works attempted to directly train the LMs within interactive decision-making environments. We aim to create an effective approach to fine-tune LMs with online reinforcement learning (RL) in these environments. We propose Reflect-RL, a two-player system to fine-tune an LM u"},"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":"2402.12621","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-20T01:04:21Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d04fa027ef9818bba87efaf1fcac000140867f102262a267999ad64d085a75e2","abstract_canon_sha256":"e03407e32a4c66ec3ade7c8d440a54b64bf9724e1bd80e5f3e3e3ec5e88ea04d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:27.056206Z","signature_b64":"2Y9n6g00EOxeiATnf3U/CylWwGkskLA6+zZoiC8VBDTTTk0lfM2Z5WcoxesSBUtP+5yPJw2pT8r+kTFSV/ePBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3910d18e8e7bf38415b46252f1ce472ec8e31072ff18355f788cee5e714ac30","last_reissued_at":"2026-07-05T08:28:27.055801Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:27.055801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reflect-RL: Two-Player Online RL Fine-Tuning for LMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Beibin Li, Runlong Zhou, Simon S. Du","submitted_at":"2024-02-20T01:04:21Z","abstract_excerpt":"As language models (LMs) demonstrate their capabilities in various fields, their application to tasks requiring multi-round interactions has become increasingly popular. These tasks usually have complex dynamics, so supervised fine-tuning (SFT) on a limited offline dataset does not yield good performance. However, only a few works attempted to directly train the LMs within interactive decision-making environments. We aim to create an effective approach to fine-tune LMs with online reinforcement learning (RL) in these environments. We propose Reflect-RL, a two-player system to fine-tune an LM u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12621","kind":"arxiv","version":2},"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/2402.12621/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":"2402.12621","created_at":"2026-07-05T08:28:27.055850+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.12621v2","created_at":"2026-07-05T08:28:27.055850+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12621","created_at":"2026-07-05T08:28:27.055850+00:00"},{"alias_kind":"pith_short_12","alias_value":"WOIQ2GHI467T","created_at":"2026-07-05T08:28:27.055850+00:00"},{"alias_kind":"pith_short_16","alias_value":"WOIQ2GHI467TQQK3","created_at":"2026-07-05T08:28:27.055850+00:00"},{"alias_kind":"pith_short_8","alias_value":"WOIQ2GHI","created_at":"2026-07-05T08:28:27.055850+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15815","citing_title":"LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra","ref_index":78,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WOIQ2GHI467TQQK3IYSS6HHEOL","json":"https://pith.science/pith/WOIQ2GHI467TQQK3IYSS6HHEOL.json","graph_json":"https://pith.science/api/pith-number/WOIQ2GHI467TQQK3IYSS6HHEOL/graph.json","events_json":"https://pith.science/api/pith-number/WOIQ2GHI467TQQK3IYSS6HHEOL/events.json","paper":"https://pith.science/paper/WOIQ2GHI"},"agent_actions":{"view_html":"https://pith.science/pith/WOIQ2GHI467TQQK3IYSS6HHEOL","download_json":"https://pith.science/pith/WOIQ2GHI467TQQK3IYSS6HHEOL.json","view_paper":"https://pith.science/paper/WOIQ2GHI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.12621&json=true","fetch_graph":"https://pith.science/api/pith-number/WOIQ2GHI467TQQK3IYSS6HHEOL/graph.json","fetch_events":"https://pith.science/api/pith-number/WOIQ2GHI467TQQK3IYSS6HHEOL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WOIQ2GHI467TQQK3IYSS6HHEOL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WOIQ2GHI467TQQK3IYSS6HHEOL/action/storage_attestation","attest_author":"https://pith.science/pith/WOIQ2GHI467TQQK3IYSS6HHEOL/action/author_attestation","sign_citation":"https://pith.science/pith/WOIQ2GHI467TQQK3IYSS6HHEOL/action/citation_signature","submit_replication":"https://pith.science/pith/WOIQ2GHI467TQQK3IYSS6HHEOL/action/replication_record"}},"created_at":"2026-07-05T08:28:27.055850+00:00","updated_at":"2026-07-05T08:28:27.055850+00:00"}