{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:L7ZR4SLJCTFQ7XNHJTBSDXU7NQ","short_pith_number":"pith:L7ZR4SLJ","schema_version":"1.0","canonical_sha256":"5ff31e496914cb0fdda74cc321de9f6c0f691ee4f0e5d7c5f8af6e728e34b395","source":{"kind":"arxiv","id":"2606.27814","version":1},"attestation_state":"computed","paper":{"title":"ATOD: Annealed Turn-aware On-policy Distillation for Multi-turn Autonomous Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Peng Chen, Qitai Tan, Yang Li, Zefang Zong","submitted_at":"2026-06-26T07:56:32Z","abstract_excerpt":"Training small language-model agents for long-horizon interactive tasks requires both fast imitation and reward-driven improvement. On-policy distillation (OPD) provides dense teacher guidance and typically improves rapidly in the early stage, but its gains saturate once the student approaches the teacher, limiting the final performance ceiling. Reinforcement learning (RL) directly optimizes environment rewards and encourages exploratory improvement toward a higher reward-defined ceiling, but sparse and delayed feedback makes early-stage learning much less efficient than OPD. In this paper, we"},"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":"2606.27814","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-26T07:56:32Z","cross_cats_sorted":[],"title_canon_sha256":"07137bfc88b783fe9c1327749f915f8b109e15e125bf68a3f0e0af1a08a18730","abstract_canon_sha256":"7896d53a9c82241450d820ebee3602d690477c8b8beb35d82b5355a96d5da9aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:49.254026Z","signature_b64":"GzLdbPvQ5dl+bqTykj8PUjQDgudniR4oHy7TH9UO2oOKDoySqaGDkwdM0L2/HzrRvy77JZIW+rexr+rpVTY0Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ff31e496914cb0fdda74cc321de9f6c0f691ee4f0e5d7c5f8af6e728e34b395","last_reissued_at":"2026-06-29T01:14:49.253617Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:49.253617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ATOD: Annealed Turn-aware On-policy Distillation for Multi-turn Autonomous Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Peng Chen, Qitai Tan, Yang Li, Zefang Zong","submitted_at":"2026-06-26T07:56:32Z","abstract_excerpt":"Training small language-model agents for long-horizon interactive tasks requires both fast imitation and reward-driven improvement. On-policy distillation (OPD) provides dense teacher guidance and typically improves rapidly in the early stage, but its gains saturate once the student approaches the teacher, limiting the final performance ceiling. Reinforcement learning (RL) directly optimizes environment rewards and encourages exploratory improvement toward a higher reward-defined ceiling, but sparse and delayed feedback makes early-stage learning much less efficient than OPD. In this paper, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27814","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/2606.27814/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":"2606.27814","created_at":"2026-06-29T01:14:49.253681+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27814v1","created_at":"2026-06-29T01:14:49.253681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27814","created_at":"2026-06-29T01:14:49.253681+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7ZR4SLJCTFQ","created_at":"2026-06-29T01:14:49.253681+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7ZR4SLJCTFQ7XNH","created_at":"2026-06-29T01:14:49.253681+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7ZR4SLJ","created_at":"2026-06-29T01:14:49.253681+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/L7ZR4SLJCTFQ7XNHJTBSDXU7NQ","json":"https://pith.science/pith/L7ZR4SLJCTFQ7XNHJTBSDXU7NQ.json","graph_json":"https://pith.science/api/pith-number/L7ZR4SLJCTFQ7XNHJTBSDXU7NQ/graph.json","events_json":"https://pith.science/api/pith-number/L7ZR4SLJCTFQ7XNHJTBSDXU7NQ/events.json","paper":"https://pith.science/paper/L7ZR4SLJ"},"agent_actions":{"view_html":"https://pith.science/pith/L7ZR4SLJCTFQ7XNHJTBSDXU7NQ","download_json":"https://pith.science/pith/L7ZR4SLJCTFQ7XNHJTBSDXU7NQ.json","view_paper":"https://pith.science/paper/L7ZR4SLJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27814&json=true","fetch_graph":"https://pith.science/api/pith-number/L7ZR4SLJCTFQ7XNHJTBSDXU7NQ/graph.json","fetch_events":"https://pith.science/api/pith-number/L7ZR4SLJCTFQ7XNHJTBSDXU7NQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7ZR4SLJCTFQ7XNHJTBSDXU7NQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7ZR4SLJCTFQ7XNHJTBSDXU7NQ/action/storage_attestation","attest_author":"https://pith.science/pith/L7ZR4SLJCTFQ7XNHJTBSDXU7NQ/action/author_attestation","sign_citation":"https://pith.science/pith/L7ZR4SLJCTFQ7XNHJTBSDXU7NQ/action/citation_signature","submit_replication":"https://pith.science/pith/L7ZR4SLJCTFQ7XNHJTBSDXU7NQ/action/replication_record"}},"created_at":"2026-06-29T01:14:49.253681+00:00","updated_at":"2026-06-29T01:14:49.253681+00:00"}