{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YLCZUBGOX4ACDFSAT667BP36CG","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":"61f5c796d69717c52e54f15d5d0c305b55ebe5d717187db73eedb576d1142b65","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T15:16:12Z","title_canon_sha256":"ba18d1513462ea056ca4699cdb59b95bb7be60ead6b71d88f89545c2dae659bf"},"schema_version":"1.0","source":{"id":"2606.03762","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03762","created_at":"2026-06-03T02:06:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03762v1","created_at":"2026-06-03T02:06:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03762","created_at":"2026-06-03T02:06:01Z"},{"alias_kind":"pith_short_12","alias_value":"YLCZUBGOX4AC","created_at":"2026-06-03T02:06:01Z"},{"alias_kind":"pith_short_16","alias_value":"YLCZUBGOX4ACDFSA","created_at":"2026-06-03T02:06:01Z"},{"alias_kind":"pith_short_8","alias_value":"YLCZUBGO","created_at":"2026-06-03T02:06:01Z"}],"graph_snapshots":[{"event_id":"sha256:c41c53f7728def45f74d2af2a2b063171fe4ff23c987ce4a0aa6b97d27001352","target":"graph","created_at":"2026-06-03T02:06:01Z","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/2606.03762/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agentic reinforcement learning (RL) equips large language models (LLMs) with tool-use capabilities that substantially improve reasoning on complex tasks. However, integrating external tools often destabilizes training: over-reliance on tools can induce input distribution shift, while overly conservative tool use limits effective exploration. To address this issue, we propose a unified framework TAO-RL that couples tool-aware trajectory filtering with entropy-guided exploration for efficient policy optimization. Specifically, at the data level, TAO-RL filters rollout trajectories along two crit","authors_text":"Haoyuan Deng, Hongye Cao, Jing Huo, Nuo Yan, Tianpei Yang, Yang Gao, Yuyao Zhang, Ziwei Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T15:16:12Z","title":"Tool-Aware Optimization with Entropy Guidance for Efficient Agentic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03762","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":"sha256:93898ae8599ef06c34c1f9f33fce728cbd7ba414795a4675e96e888ab35bb8de","target":"record","created_at":"2026-06-03T02:06:01Z","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":"61f5c796d69717c52e54f15d5d0c305b55ebe5d717187db73eedb576d1142b65","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T15:16:12Z","title_canon_sha256":"ba18d1513462ea056ca4699cdb59b95bb7be60ead6b71d88f89545c2dae659bf"},"schema_version":"1.0","source":{"id":"2606.03762","kind":"arxiv","version":1}},"canonical_sha256":"c2c59a04cebf002196409fbdf0bf7e118194f97e9575eaef8880d293ea7c9b1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2c59a04cebf002196409fbdf0bf7e118194f97e9575eaef8880d293ea7c9b1c","first_computed_at":"2026-06-03T02:06:01.764197Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T02:06:01.764197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0nmSEdjp7WVxckT3ic1gic2kTMVCEZUA12DbeeNpmV8qLiHoqiiA80BYWucIQjWtKGBmRdXDBvrVhe5dPqiEDw==","signature_status":"signed_v1","signed_at":"2026-06-03T02:06:01.764642Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03762","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93898ae8599ef06c34c1f9f33fce728cbd7ba414795a4675e96e888ab35bb8de","sha256:c41c53f7728def45f74d2af2a2b063171fe4ff23c987ce4a0aa6b97d27001352"],"state_sha256":"fd295afa122bcc9436a5718c1cf4429e12cff7afd82cc12b25076d9528317137"}