{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7XLYZ6UQHGOAUWLRFYPEWEVNKD","short_pith_number":"pith:7XLYZ6UQ","schema_version":"1.0","canonical_sha256":"fdd78cfa90399c0a59712e1e4b12ad50d8d3675a8a6b1bdc0fb63b8cff0f582e","source":{"kind":"arxiv","id":"2606.09961","version":1},"attestation_state":"computed","paper":{"title":"3SPO: State-Score-Supervised Policy Optimization for LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kailing Li, Linhai Zhuo, Tianwen Qian, Yang Jiao, Yu Han, Yulin Dai, Yuqian Fu","submitted_at":"2026-06-08T14:26:05Z","abstract_excerpt":"Training large language models (LLMs) as autonomous agents via reinforcement learning (RL) has enabled frontier models to achieve superhuman performance in long-horizon tasks. However, existing RL algorithms operate at the trajectory level, performing policy optimization only after collecting complete episode rollouts. This coarse-grained approach faces fundamental challenges in multi-turn agent settings where rewards are sparse, delayed, and credit assignment across individual steps is critical. In this work, we propose \\textbf{State-Score-Supervised Policy Optimization (3SPO)}, a novel RL al"},"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":"2606.09961","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T14:26:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7538a0988cae31c880280d92e335152f7aa202ac6cdf010322c0384a6c33bbaa","abstract_canon_sha256":"43f3fb13978a8e150f923b3a597bc8075e50dac3cd6f9ea3091f517605cc38c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T00:08:35.131823Z","signature_b64":"goEE+Xf27baGYQc4ZSQtaaJZTCrdbZJNenThOTRfUw8dkuq/w0S9mbCNF9BNQx36ECyyy71BPDfDpUAyzLvAAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdd78cfa90399c0a59712e1e4b12ad50d8d3675a8a6b1bdc0fb63b8cff0f582e","last_reissued_at":"2026-06-10T00:08:35.130902Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T00:08:35.130902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3SPO: State-Score-Supervised Policy Optimization for LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kailing Li, Linhai Zhuo, Tianwen Qian, Yang Jiao, Yu Han, Yulin Dai, Yuqian Fu","submitted_at":"2026-06-08T14:26:05Z","abstract_excerpt":"Training large language models (LLMs) as autonomous agents via reinforcement learning (RL) has enabled frontier models to achieve superhuman performance in long-horizon tasks. However, existing RL algorithms operate at the trajectory level, performing policy optimization only after collecting complete episode rollouts. This coarse-grained approach faces fundamental challenges in multi-turn agent settings where rewards are sparse, delayed, and credit assignment across individual steps is critical. In this work, we propose \\textbf{State-Score-Supervised Policy Optimization (3SPO)}, a novel RL al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09961","kind":"arxiv","version":1},"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/2606.09961/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":"2606.09961","created_at":"2026-06-10T00:08:35.131048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09961v1","created_at":"2026-06-10T00:08:35.131048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09961","created_at":"2026-06-10T00:08:35.131048+00:00"},{"alias_kind":"pith_short_12","alias_value":"7XLYZ6UQHGOA","created_at":"2026-06-10T00:08:35.131048+00:00"},{"alias_kind":"pith_short_16","alias_value":"7XLYZ6UQHGOAUWLR","created_at":"2026-06-10T00:08:35.131048+00:00"},{"alias_kind":"pith_short_8","alias_value":"7XLYZ6UQ","created_at":"2026-06-10T00:08:35.131048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7XLYZ6UQHGOAUWLRFYPEWEVNKD","json":"https://pith.science/pith/7XLYZ6UQHGOAUWLRFYPEWEVNKD.json","graph_json":"https://pith.science/api/pith-number/7XLYZ6UQHGOAUWLRFYPEWEVNKD/graph.json","events_json":"https://pith.science/api/pith-number/7XLYZ6UQHGOAUWLRFYPEWEVNKD/events.json","paper":"https://pith.science/paper/7XLYZ6UQ"},"agent_actions":{"view_html":"https://pith.science/pith/7XLYZ6UQHGOAUWLRFYPEWEVNKD","download_json":"https://pith.science/pith/7XLYZ6UQHGOAUWLRFYPEWEVNKD.json","view_paper":"https://pith.science/paper/7XLYZ6UQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09961&json=true","fetch_graph":"https://pith.science/api/pith-number/7XLYZ6UQHGOAUWLRFYPEWEVNKD/graph.json","fetch_events":"https://pith.science/api/pith-number/7XLYZ6UQHGOAUWLRFYPEWEVNKD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7XLYZ6UQHGOAUWLRFYPEWEVNKD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7XLYZ6UQHGOAUWLRFYPEWEVNKD/action/storage_attestation","attest_author":"https://pith.science/pith/7XLYZ6UQHGOAUWLRFYPEWEVNKD/action/author_attestation","sign_citation":"https://pith.science/pith/7XLYZ6UQHGOAUWLRFYPEWEVNKD/action/citation_signature","submit_replication":"https://pith.science/pith/7XLYZ6UQHGOAUWLRFYPEWEVNKD/action/replication_record"}},"created_at":"2026-06-10T00:08:35.131048+00:00","updated_at":"2026-06-10T00:08:35.131048+00:00"}