{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_236b4575e183fbce599ce32467887a1fe5f3166e2b3b29d21163ddfd3a77999f","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_236b4575e183fbce599ce32467887a1fe5f3166e2b3b29d21163ddfd3a77999f","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"8c78a9810147feef5729784247ebb320ae4bd8b11386716bf5b5a25930a00585","published":"Mon, 29 Jun 2026 00:00:00 -0400","receipt_hash":"8c78a9810147feef5729784247ebb320ae4bd8b11386716bf5b5a25930a00585","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"8c78a9810147feef5729784247ebb320ae4bd8b11386716bf5b5a25930a00585","observed_at":"2026-06-29T04:44:03.414425Z","parent_run_hash":"36b5ab5c57ae76dc9e1a863501c4d38f172868cfae31b4ba5baf3caffaafb2c4","published":"Mon, 29 Jun 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2606.27814v1 Announce Type: new \nAbstract: 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 propose ATOD (Annealed Turn-aware On-policy Distillation), a hybrid online distillation algorithm that explicitly exploits this complementarity. (1) ATOD uses an annealed OPD-RL schedule: OPD dominates early training to approach teacher-level behavior, while RL is gradually strengthened to drive reward-based exploration. (2) ATOD introduces Turn-le","title":"ATOD: Annealed Turn-aware On-policy Distillation for Multi-turn Autonomous Agents","url":"https://arxiv.org/abs/2606.27814","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.27814v1 Announce Type: new \nAbstract: 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 propose ATOD (Annealed Turn-aware On-policy Distillation), a hybrid online distillation algorithm that explicitly exploits this complementarity. (1) ATOD uses an annealed OPD-RL schedule: OPD dominates early training to approach teacher-level behavior, while RL is gradually strengthened to drive reward-based exploration. (2) ATOD introduces Turn-le","title":"ATOD: Annealed Turn-aware On-policy Distillation for Multi-turn Autonomous Agents","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-29T04:44:03Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.27814"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:7a977f7c477e9ea75dbe6f0cd525e0f6039681fb596a3617f58eff60ecb97cdf8c2d102cdc4be4a609fb4e645dfd6dede4a3b26bba523c2a7891406b7550c500","signer":"crovia.substrate","subject":{"observed_at":"2026-06-29T04:44:03Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.27814"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"27f25ab5eb37651f87d31e7f225cb60327a4080775e88c29a74095044b12c116","leaf_index":261325,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"28ff9ec874aea819a6ff4dbd4c62e72de0b59a7843fcf69edd25860890bda176","side":"left"},{"sibling":"7135b2b967e62fe9437c80aaef5335059868b4b761ef6da7643b357ef0a8111d","side":"right"},{"sibling":"1d89657b4732f858dff3b963083c63f540069a0f69972b6ebaf7ed73a1315e95","side":"left"},{"sibling":"b6ffda0cee599b273ce6d588480422a1447a4a3b2b44e26aa53c1f689b792617","side":"left"},{"sibling":"93b6bf876239c0606054ab0f6535d3be4fe46bcd07bb22bdb0ba6eb747bd594f","side":"right"},{"sibling":"29e91c8cbbd7b5d986a89514acfb133bc4553933f559284c7b35fe66f2970db0","side":"right"},{"sibling":"ab8f67f857fa81c6ddd6431b5feff1b6dea6f58d2d6384543bad28001936ae23","side":"left"},{"sibling":"daf5279d003dd81baccfe21e3bfac0a3b468c08210a2f76237353b11695cdd73","side":"left"},{"sibling":"3698d5368a778dfd474a1084879c71ccc04d1602253019e48bab7329c680972f","side":"right"},{"sibling":"9f9daa9d12e65b219f34c92aec45450536b79a42b8892050d66961432ae28ed1","side":"right"},{"sibling":"b5725d7b0807dc6da32d9788f20057fa8726be38d30a9ebdabc605ae92739122","side":"left"},{"sibling":"e321b2cac14cbe28f76ccb7938249a40ff60cd5d2128b5634be046ea10e984b8","side":"left"},{"sibling":"5900dc6c7d13855af9d0385baf1691ec386df33e450c422af1cabe0a36e40ad8","side":"left"},{"sibling":"ae636ddee98c71ab7a7dc55ddfab70c7f710a2b6abfdf7a8b5d16a4017d1c0d1","side":"left"},{"sibling":"f29798d8bb6aa9900eab878992d9ff0c53266debd87472f31ab26a6a3fb55880","side":"left"},{"sibling":"a04392fb9f2a3a620840e3b3fecd93d12e6d224e481c162389d8ae64e7194599","side":"left"},{"sibling":"c300cf0154c136afc09b1702a0be98f4ba5b6dc5cf57e8cc714ec1eaf4196eff","side":"left"},{"sibling":"d841ad93efda0869e5eb97678f348f03f5caab4353e05ff4bf18f47fb945b822","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":261662,"merkle_root":"aa8865c239aa2eb6c8aa7c6250f56b3cd5709854a8a07f6a29eb4ddd8802cb6f","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260629T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-29T05:38:02Z","sig_algorithm":"ed25519","signature":"476329233e82fb35fba2552ddc5d1d75b2bdd8513bbd281e9c40a0b8e475df374a62dcd8b456b0c5e8815984f5b4bf0983ae95d2cf4d7412ebb13a433b933c0a","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_236b4575e183fbce599ce32467887a1fe5f3166e2b3b29d21163ddfd3a77999f"}}