{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5HR2OWWAWOLT2OJHB4NBQ4ZGL7","short_pith_number":"pith:5HR2OWWA","schema_version":"1.0","canonical_sha256":"e9e3a75ac0b3973d39270f1a1873265fd97fcdf6fa3dfb944f931a03a1723825","source":{"kind":"arxiv","id":"2606.02994","version":1},"attestation_state":"computed","paper":{"title":"Inducing Reasoning Primitives from Agent Traces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jiarui Yan, Joshua Momo, William W. Cohen, Zhihan Lei","submitted_at":"2026-06-02T01:11:15Z","abstract_excerpt":"ReAct-style LLM agents often rediscover the same reasoning routines across problems, yet leave those routines trapped in transient scratchpads. We introduce Reasoning Primitive Induction, a single-pass method that mines successful ReAct traces, clusters recurrent reasoning moves, and converts the most frequent moves into a compact library of typed pseudo-tools. Each pseudo-tool is specified by a natural-language docstring interpreted by an LLM at invocation time, and a standard ReAct loop composes these primitives at test time. The central result is that induced libraries outperform the very a"},"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":"2606.02994","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T01:11:15Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"03c1b9487c79df2dadf7335095141e77410a14333cdfcb5ac4cc0343d37607a4","abstract_canon_sha256":"54dc4c6d57b73c1c55dd2875dc624839c7d4d4221e08d2caad590fd1ac2db7f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:28.781037Z","signature_b64":"CkukHh21TzKsaoxNkfDjgp6upDaJpmunvlR1lZgnAuL6kUDsNkqBPfHL/3M2ughpXRAfoCj6aG8sNSSMkUuDDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9e3a75ac0b3973d39270f1a1873265fd97fcdf6fa3dfb944f931a03a1723825","last_reissued_at":"2026-06-03T01:05:28.780652Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:28.780652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inducing Reasoning Primitives from Agent Traces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jiarui Yan, Joshua Momo, William W. Cohen, Zhihan Lei","submitted_at":"2026-06-02T01:11:15Z","abstract_excerpt":"ReAct-style LLM agents often rediscover the same reasoning routines across problems, yet leave those routines trapped in transient scratchpads. We introduce Reasoning Primitive Induction, a single-pass method that mines successful ReAct traces, clusters recurrent reasoning moves, and converts the most frequent moves into a compact library of typed pseudo-tools. Each pseudo-tool is specified by a natural-language docstring interpreted by an LLM at invocation time, and a standard ReAct loop composes these primitives at test time. The central result is that induced libraries outperform the very a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02994","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/2606.02994/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":"2606.02994","created_at":"2026-06-03T01:05:28.780701+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02994v1","created_at":"2026-06-03T01:05:28.780701+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02994","created_at":"2026-06-03T01:05:28.780701+00:00"},{"alias_kind":"pith_short_12","alias_value":"5HR2OWWAWOLT","created_at":"2026-06-03T01:05:28.780701+00:00"},{"alias_kind":"pith_short_16","alias_value":"5HR2OWWAWOLT2OJH","created_at":"2026-06-03T01:05:28.780701+00:00"},{"alias_kind":"pith_short_8","alias_value":"5HR2OWWA","created_at":"2026-06-03T01:05:28.780701+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/5HR2OWWAWOLT2OJHB4NBQ4ZGL7","json":"https://pith.science/pith/5HR2OWWAWOLT2OJHB4NBQ4ZGL7.json","graph_json":"https://pith.science/api/pith-number/5HR2OWWAWOLT2OJHB4NBQ4ZGL7/graph.json","events_json":"https://pith.science/api/pith-number/5HR2OWWAWOLT2OJHB4NBQ4ZGL7/events.json","paper":"https://pith.science/paper/5HR2OWWA"},"agent_actions":{"view_html":"https://pith.science/pith/5HR2OWWAWOLT2OJHB4NBQ4ZGL7","download_json":"https://pith.science/pith/5HR2OWWAWOLT2OJHB4NBQ4ZGL7.json","view_paper":"https://pith.science/paper/5HR2OWWA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02994&json=true","fetch_graph":"https://pith.science/api/pith-number/5HR2OWWAWOLT2OJHB4NBQ4ZGL7/graph.json","fetch_events":"https://pith.science/api/pith-number/5HR2OWWAWOLT2OJHB4NBQ4ZGL7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5HR2OWWAWOLT2OJHB4NBQ4ZGL7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5HR2OWWAWOLT2OJHB4NBQ4ZGL7/action/storage_attestation","attest_author":"https://pith.science/pith/5HR2OWWAWOLT2OJHB4NBQ4ZGL7/action/author_attestation","sign_citation":"https://pith.science/pith/5HR2OWWAWOLT2OJHB4NBQ4ZGL7/action/citation_signature","submit_replication":"https://pith.science/pith/5HR2OWWAWOLT2OJHB4NBQ4ZGL7/action/replication_record"}},"created_at":"2026-06-03T01:05:28.780701+00:00","updated_at":"2026-06-03T01:05:28.780701+00:00"}