{"_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_f91c01ebb57d3d98a578b85251454e9a3ee4c7209062974cf172537c40fd68cf","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_f91c01ebb57d3d98a578b85251454e9a3ee4c7209062974cf172537c40fd68cf","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"8c1755c8dec03fa0f07dab14704118bc72968ff72f040e28da57bd71b62a6e38","published":"Fri, 15 May 2026 00:00:00 -0400","receipt_hash":"8c1755c8dec03fa0f07dab14704118bc72968ff72f040e28da57bd71b62a6e38","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":"8c1755c8dec03fa0f07dab14704118bc72968ff72f040e28da57bd71b62a6e38","observed_at":"2026-05-15T04:43:17.611638Z","parent_run_hash":"5c64f85625fabd323e9c4a1cf068c012fb88a248deda9a9ac702fb2f9799f2e5","published":"Fri, 15 May 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:2605.15155v1 Announce Type: cross \nAbstract: Reinforcement learning (RL) has emerged as a central paradigm for post-training LLM agents, yet its trajectory-level reward signal provides only coarse supervision for long-horizon interaction. On-Policy Self-Distillation (OPSD) complements RL by introducing dense token-level guidance from a teacher branch augmented with privileged context. However, transferring OPSD to multi-turn agents proves problematic: compounding multi-turn instability destabilizes supervision, while skill-conditioned privileged guidance requires asymmetric treatment for negative teacher rejections may arise from imperfect skills retrieval or utilization. We introduce SDAR (Self-Distilled Agentic Reinforcement Learning), which treats OPSD as a gated auxiliary objective while keeping RL as the primary optimization backbone. SDAR maps detached token-level signals into a sigmoid gate, strengthening distillation on teacher-endorsed positive-gap tokens and softly atte","title":"Self-Distilled Agentic Reinforcement Learning","url":"https://arxiv.org/abs/2605.15155","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.15155v1 Announce Type: cross \nAbstract: Reinforcement learning (RL) has emerged as a central paradigm for post-training LLM agents, yet its trajectory-level reward signal provides only coarse supervision for long-horizon interaction. On-Policy Self-Distillation (OPSD) complements RL by introducing dense token-level guidance from a teacher branch augmented with privileged context. However, transferring OPSD to multi-turn agents proves problematic: compounding multi-turn instability destabilizes supervision, while skill-conditioned privileged guidance requires asymmetric treatment for negative teacher rejections may arise from imperfect skills retrieval or utilization. We introduce SDAR (Self-Distilled Agentic Reinforcement Learning), which treats OPSD as a gated auxiliary objective while keeping RL as the primary optimization backbone. SDAR maps detached token-level signals into a sigmoid gate, strengthening distillation on teacher-endorsed positive-gap tokens and softly atte","title":"Self-Distilled Agentic Reinforcement Learning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-15T04:43:17Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.15155"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:5d4c28f8fc3f8bc98f01ced30a436ca5c340b1819ba4c2f7c279ce961178f4cbe335059814aaa3e58765a12204f8229bc1bcd5543405ae8a022bed63ce09d20c","signer":"crovia.substrate","subject":{"observed_at":"2026-05-15T04:43:17Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.15155"},"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":"dcceded38e9cea5857b360c23abeeda6a30b5ead5bcaafc8cd12724b39e4850f","leaf_index":134673,"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":"cb6817af915de2d7bc9dbb89f91778b683a83f35fccd11c6cb9e48f35443f612","side":"left"},{"sibling":"b0c588cf52db8ba91e39167a93ef2eaf1f8ed4725cc83fabd4f971f82045efa3","side":"right"},{"sibling":"dcf2ba00d6d30b2eaacac5aa60349c823c5e1e32f895bd189b4cf5ea3bfc276b","side":"right"},{"sibling":"743e69d813dc525cc4236c95078aea6f0ff1eb70e073e112b17194d508088565","side":"right"},{"sibling":"bed02182385a9a1ea96260612655f90a7cfffda12c0023f387b0f235b61bf408","side":"left"},{"sibling":"ccf3ee4ca5cc4d59521386cf1a31e9f523148c2cc92f5ee2750b82f33475d591","side":"right"},{"sibling":"bca4711cdb0765a339b3db05a85ed17fb8e65a24e2b58309e8137da50874715e","side":"right"},{"sibling":"d8ac22bfe982d5dc7f00879b0b1dfae8f4e95a38a6242933cbebb3b7271d5704","side":"right"},{"sibling":"a17a0eaa87574a308e2c02cf125072b9e69566b9e8d6d2e64a02880192b885d5","side":"right"},{"sibling":"6bd0475fd3a73322a4f73095c96b072de89e462ce5839161aa552e0208619bce","side":"left"},{"sibling":"36672459e5ed50c64ee1842b69cb6d2eb682c2a04844555be8d124257571994a","side":"left"},{"sibling":"727783827652adfa99c455bd80a01bfb33836228e51068b4f654ef3da468ca69","side":"left"},{"sibling":"623194cd30880ed223e306737fdb111aa0d781751bfc47553c404a6af6aad2c4","side":"right"},{"sibling":"fc8f53ed42756907fb79ee19a4ed09f72c560e5302b3d98198b96bf1da635a4a","side":"right"},{"sibling":"d6607539da7ba39ec68be2d12f27ed6768766c745e3120fd915f88c5e288e07c","side":"right"},{"sibling":"b63408a424d27cd6a75e0fb155e69a58a328f41e9cb9dba1eddef9a5289cc7fd","side":"right"},{"sibling":"356fb36a4e188f03d7a05c54cd8789bdd40eda454b9bc9560f667acc08e6c4e0","side":"right"},{"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":134886,"merkle_root":"c6c7ae28c065bced89e7f844216b073f1a7cc4b378db0d41a98bcd21b28066db","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260515T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-15T05:37:26Z","sig_algorithm":"ed25519","signature":"5a3978c26017daf4104adbb3e1c3099c5750157acbfc7242ece1815dc6740fe08a690291ce0afe42011e20cc565b5ebe64ec016bf658b5bab563a63337985c05","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_f91c01ebb57d3d98a578b85251454e9a3ee4c7209062974cf172537c40fd68cf"}}