{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UFG4QA677KTFAZC2MQV7JAVO2O","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":"890039b03550cd0ab2397efff3035261f9254ae0ba9fc8bd2c4fd958bc554463","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-07T12:47:23Z","title_canon_sha256":"1d04a696dc868d1021a5d8e0971178174440e58885a13a9a8b6099aaef6ad31f"},"schema_version":"1.0","source":{"id":"2607.06223","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.06223","created_at":"2026-07-08T01:19:18Z"},{"alias_kind":"arxiv_version","alias_value":"2607.06223v1","created_at":"2026-07-08T01:19:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06223","created_at":"2026-07-08T01:19:18Z"},{"alias_kind":"pith_short_12","alias_value":"UFG4QA677KTF","created_at":"2026-07-08T01:19:18Z"},{"alias_kind":"pith_short_16","alias_value":"UFG4QA677KTFAZC2","created_at":"2026-07-08T01:19:18Z"},{"alias_kind":"pith_short_8","alias_value":"UFG4QA67","created_at":"2026-07-08T01:19:18Z"}],"graph_snapshots":[{"event_id":"sha256:24461b9dde5eff64ec2120270654b768df5f59f4e50c5fbc77707bab305de84d","target":"graph","created_at":"2026-07-08T01:19:18Z","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/2607.06223/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning has become a promising paradigm for improving large language model (LLM) agents on long-horizon search tasks, where the agent must make a sequence of intermediate decisions before receiving a final outcome. However, existing methods still face a key limitation: the rollout budget is often allocated without explicitly assessing the utility of intermediate states. As a result, substantial computation may be spent on low-value states, even though different branches can vary drastically in their informativeness. In this paper, we propose Information Gain-based Rollout Policy","authors_text":"Fan Xu, Haoxiang Zhang, Jiaxin Ding, Luoyi Fu, Shiqing Gao, Xinbing Wang, Xin Ding, Yijun Zhang, Yule Xie","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-07T12:47:23Z","title":"Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06223","kind":"arxiv","version":1},"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":"sha256:7605594a863be615ac36f6544958314f1cf5b891f9e933c8cf7c96f1a548b671","target":"record","created_at":"2026-07-08T01:19:18Z","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":"890039b03550cd0ab2397efff3035261f9254ae0ba9fc8bd2c4fd958bc554463","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-07T12:47:23Z","title_canon_sha256":"1d04a696dc868d1021a5d8e0971178174440e58885a13a9a8b6099aaef6ad31f"},"schema_version":"1.0","source":{"id":"2607.06223","kind":"arxiv","version":1}},"canonical_sha256":"a14dc803dffaa650645a642bf482aed385e240e16749b38d3ec7ae2387c002e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a14dc803dffaa650645a642bf482aed385e240e16749b38d3ec7ae2387c002e3","first_computed_at":"2026-07-08T01:19:18.268744Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-08T01:19:18.268744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c9hl67ZLKos/hYoQQPv+3KyNzG9wRAWVvslInsgVuwMiWQ448IB/OELsfnWteRJUAoEeLtnkuLCggTGZGbBQAQ==","signature_status":"signed_v1","signed_at":"2026-07-08T01:19:18.269157Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.06223","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7605594a863be615ac36f6544958314f1cf5b891f9e933c8cf7c96f1a548b671","sha256:24461b9dde5eff64ec2120270654b768df5f59f4e50c5fbc77707bab305de84d"],"state_sha256":"b07ad04150457b528c1dd21d7c96d0e721156a496cb0cecd69e3180f72925bdb"}