{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:R5WNUQXTRVNE6DNUPFUXVOMK37","short_pith_number":"pith:R5WNUQXT","schema_version":"1.0","canonical_sha256":"8f6cda42f38d5a4f0db479697ab98adfe5cf14f6cdecf35467e4618627c1931a","source":{"kind":"arxiv","id":"2606.06976","version":1},"attestation_state":"computed","paper":{"title":"Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dongrui Liu, Jing Shao, Junchi Yan, Linqian Zeng, Wenyuan Xie, Xiaoya Lu, Yijin Zhou","submitted_at":"2026-06-05T07:08:34Z","abstract_excerpt":"Large language model (LLM)-based agents often make suboptimal tool-use decisions, including unsupported tool invocation and hallucinated direct responses, which may accumulate errors throughout multi-step interactions. Existing approaches mainly improve these behaviors through inference-time correction or coarse-grained reward signals based on decision outcomes and structured checklists, leaving the uncertainty characteristics of agent decisions underexplored. We observe that decision-oriented reinforcement learning tends to weaken the uncertainty separation between correct and incorrect actio"},"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":"2606.06976","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-05T07:08:34Z","cross_cats_sorted":[],"title_canon_sha256":"012f61c6a1e764491eaa1fe0c5bd92bca1583833008b05104516c661087803cb","abstract_canon_sha256":"e858c08c760ab6271845e92409a5bb5922e57c1756908423e84f53bea5aaf788"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:39.054856Z","signature_b64":"3U27gtp73SMGwt3ZETz6X4mTPNrMdn0ZQXhJGXCLQpHZMd4ozD1vSxjL0WAHc2JPYmbrFuq5B9zSQjtSmbGdCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f6cda42f38d5a4f0db479697ab98adfe5cf14f6cdecf35467e4618627c1931a","last_reissued_at":"2026-06-08T01:04:39.054284Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:39.054284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dongrui Liu, Jing Shao, Junchi Yan, Linqian Zeng, Wenyuan Xie, Xiaoya Lu, Yijin Zhou","submitted_at":"2026-06-05T07:08:34Z","abstract_excerpt":"Large language model (LLM)-based agents often make suboptimal tool-use decisions, including unsupported tool invocation and hallucinated direct responses, which may accumulate errors throughout multi-step interactions. Existing approaches mainly improve these behaviors through inference-time correction or coarse-grained reward signals based on decision outcomes and structured checklists, leaving the uncertainty characteristics of agent decisions underexplored. We observe that decision-oriented reinforcement learning tends to weaken the uncertainty separation between correct and incorrect actio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06976","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/2606.06976/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":"2606.06976","created_at":"2026-06-08T01:04:39.054352+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06976v1","created_at":"2026-06-08T01:04:39.054352+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06976","created_at":"2026-06-08T01:04:39.054352+00:00"},{"alias_kind":"pith_short_12","alias_value":"R5WNUQXTRVNE","created_at":"2026-06-08T01:04:39.054352+00:00"},{"alias_kind":"pith_short_16","alias_value":"R5WNUQXTRVNE6DNU","created_at":"2026-06-08T01:04:39.054352+00:00"},{"alias_kind":"pith_short_8","alias_value":"R5WNUQXT","created_at":"2026-06-08T01:04:39.054352+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/R5WNUQXTRVNE6DNUPFUXVOMK37","json":"https://pith.science/pith/R5WNUQXTRVNE6DNUPFUXVOMK37.json","graph_json":"https://pith.science/api/pith-number/R5WNUQXTRVNE6DNUPFUXVOMK37/graph.json","events_json":"https://pith.science/api/pith-number/R5WNUQXTRVNE6DNUPFUXVOMK37/events.json","paper":"https://pith.science/paper/R5WNUQXT"},"agent_actions":{"view_html":"https://pith.science/pith/R5WNUQXTRVNE6DNUPFUXVOMK37","download_json":"https://pith.science/pith/R5WNUQXTRVNE6DNUPFUXVOMK37.json","view_paper":"https://pith.science/paper/R5WNUQXT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06976&json=true","fetch_graph":"https://pith.science/api/pith-number/R5WNUQXTRVNE6DNUPFUXVOMK37/graph.json","fetch_events":"https://pith.science/api/pith-number/R5WNUQXTRVNE6DNUPFUXVOMK37/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R5WNUQXTRVNE6DNUPFUXVOMK37/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R5WNUQXTRVNE6DNUPFUXVOMK37/action/storage_attestation","attest_author":"https://pith.science/pith/R5WNUQXTRVNE6DNUPFUXVOMK37/action/author_attestation","sign_citation":"https://pith.science/pith/R5WNUQXTRVNE6DNUPFUXVOMK37/action/citation_signature","submit_replication":"https://pith.science/pith/R5WNUQXTRVNE6DNUPFUXVOMK37/action/replication_record"}},"created_at":"2026-06-08T01:04:39.054352+00:00","updated_at":"2026-06-08T01:04:39.054352+00:00"}