{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IZORAA2TKSCMWDLH3SVMNLPKNF","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":"9f5472d381d7dae585da1eb8dd911a758f6cc6d72267d5dc9bd08e53a0883c30","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T11:58:55Z","title_canon_sha256":"d9964c827ba10a7d3a04452ff9bf28ee36a83f8bc38c59ca3833d18fdef1b550"},"schema_version":"1.0","source":{"id":"2606.02132","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.02132","created_at":"2026-06-02T02:05:07Z"},{"alias_kind":"arxiv_version","alias_value":"2606.02132v1","created_at":"2026-06-02T02:05:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02132","created_at":"2026-06-02T02:05:07Z"},{"alias_kind":"pith_short_12","alias_value":"IZORAA2TKSCM","created_at":"2026-06-02T02:05:07Z"},{"alias_kind":"pith_short_16","alias_value":"IZORAA2TKSCMWDLH","created_at":"2026-06-02T02:05:07Z"},{"alias_kind":"pith_short_8","alias_value":"IZORAA2T","created_at":"2026-06-02T02:05:07Z"}],"graph_snapshots":[{"event_id":"sha256:04985903dbdcd9ff866f660f4b7b58c0b72703c7917abf9937c50c7147acde17","target":"graph","created_at":"2026-06-02T02:05:07Z","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/2606.02132/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agentic reinforcement learning can induce tool abuse, where models overuse external tools even for queries solvable by internal reasoning. Existing approaches mitigate this issue with uniform tool-use penalties or hard limits, which reduce tool frequency but may also suppress useful tool-assisted exploration. We propose EAPO, an Efficient Agentic Policy Optimization framework that learns selective tool use. EAPO introduces tool-free trajectories into each rollout group, applies difficulty-aware reward shaping to penalize redundant tool calls mainly on easier queries, and uses confidence-aware ","authors_text":"Dianxing Tang, Dingshuo Chen, Liang Wang, Liuji Chen, Qiang Liu, Shu Wu, Xing Shi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T11:58:55Z","title":"Learning When Not to Act: Mitigating Tool Abuse in Agentic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02132","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:f73c5717530ab0b350c7b50b6eb2b34dfb3b045a63f52cc272ed0e0c76eed90e","target":"record","created_at":"2026-06-02T02:05:07Z","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":"9f5472d381d7dae585da1eb8dd911a758f6cc6d72267d5dc9bd08e53a0883c30","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T11:58:55Z","title_canon_sha256":"d9964c827ba10a7d3a04452ff9bf28ee36a83f8bc38c59ca3833d18fdef1b550"},"schema_version":"1.0","source":{"id":"2606.02132","kind":"arxiv","version":1}},"canonical_sha256":"465d1003535484cb0d67dcaac6adea6960c232b65e9f06ee3c3ae489d81b45a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"465d1003535484cb0d67dcaac6adea6960c232b65e9f06ee3c3ae489d81b45a4","first_computed_at":"2026-06-02T02:05:07.340464Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:05:07.340464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dRKNW4MnSjQNGEkug+dSM0yud9qpAWusWsSiC3x2MK4AQnQ6bmNgzNeNG9RS+xpv9GMjbeuNje3egDqMg5cYBw==","signature_status":"signed_v1","signed_at":"2026-06-02T02:05:07.340858Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.02132","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f73c5717530ab0b350c7b50b6eb2b34dfb3b045a63f52cc272ed0e0c76eed90e","sha256:04985903dbdcd9ff866f660f4b7b58c0b72703c7917abf9937c50c7147acde17"],"state_sha256":"b7e01c9cf2998e3c295ff57d70cc968015b046cbdcf5557123060ea3e0f788fb"}