{"_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_20b15dba8d2c77f4edb8eddbbd8914c47c3cc02286f499130ac8573ba30a7a4a","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_20b15dba8d2c77f4edb8eddbbd8914c47c3cc02286f499130ac8573ba30a7a4a","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"23a79e75b7e5ce459e1e4c536abb8632b7f7fe134ea453b358b77b30a17ed248","published":"Wed, 10 Jun 2026 00:00:00 -0400","receipt_hash":"23a79e75b7e5ce459e1e4c536abb8632b7f7fe134ea453b358b77b30a17ed248","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":"23a79e75b7e5ce459e1e4c536abb8632b7f7fe134ea453b358b77b30a17ed248","observed_at":"2026-06-10T04:43:37.461885Z","parent_run_hash":"23aff1a6f676ba7ca33f70f4ddfae1dd282fb86104d577ce9be510d81a94c5dc","published":"Wed, 10 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:2606.11119v1 Announce Type: cross \nAbstract: Reinforcement learning with verifiable rewards (RLVR) is a promising approach for enhancing reasoning and agentic behavior in large language models. However, rollout-intensive policy optimization is often limited by insufficient reward contrast, arising when overly simple or complex prompts generate low-variance feedback and when outcome-only rewards assign the same terminal assessment to every decision in a multi-turn rollout. Past efforts have focused on allocating available rollout resources to promising prompts, yet they only leverage sample informativeness at the prompt level and neglect variation in prefix-level informativeness across turns within the same rollout. This work targets multi-turn agentic RL by modeling each ReAct-style thought-action-observation turn as a semantically distinct node, allowing budget allocation to extend from prompt roots to turn-level prefixes with further continuations, which naturally forms tree-st","title":"TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning","url":"https://arxiv.org/abs/2606.11119","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.11119v1 Announce Type: cross \nAbstract: Reinforcement learning with verifiable rewards (RLVR) is a promising approach for enhancing reasoning and agentic behavior in large language models. However, rollout-intensive policy optimization is often limited by insufficient reward contrast, arising when overly simple or complex prompts generate low-variance feedback and when outcome-only rewards assign the same terminal assessment to every decision in a multi-turn rollout. Past efforts have focused on allocating available rollout resources to promising prompts, yet they only leverage sample informativeness at the prompt level and neglect variation in prefix-level informativeness across turns within the same rollout. This work targets multi-turn agentic RL by modeling each ReAct-style thought-action-observation turn as a semantically distinct node, allowing budget allocation to extend from prompt roots to turn-level prefixes with further continuations, which naturally forms tree-st","title":"TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-10T04:43:37Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.11119"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:71ead2e24d2c8635237fc9a2a45b1b1dbf8499300c9ba7e87753f7b3052327d97d2239d9b7276c5c78d2d0a159ee44e807afc1e4365a416fe18729bcb3d2570f","signer":"crovia.substrate","subject":{"observed_at":"2026-06-10T04:43:37Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.11119"},"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":"a3bd82a6f0d46ad35284d1f770a8b07c1cbaa3af136e37b0a56dea45c95e3a5b","leaf_index":226117,"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":"d99203df6c56085979344258fe8c9996aa132fc239b678220042049041cceeeb","side":"left"},{"sibling":"bfb7a06d6aa31d7af56a35d7d2d15362548b9f3f0e8072de2f13d84286fb12eb","side":"right"},{"sibling":"7e152442260aff6edde5b3d65f594a2b69b3e7760ecce7d3cd54474c361920e7","side":"left"},{"sibling":"d9569c8a27122c36d7c76e9ee91e4d18c75af69a7dfcafb3e5617c1de1d369ea","side":"right"},{"sibling":"6d61498a9373367fb4b6e32566ee2038009bcb6b611b7792a9304910ea09b9be","side":"right"},{"sibling":"2ee12d5b009abe0086e35e2ae134b79dd68d8a6bf6849547e4b0c90973f95c98","side":"right"},{"sibling":"c20ffe9501388a4e560b300f20c62c7cd1bd74b8c3502a50047853354b09279c","side":"left"},{"sibling":"670eed753a274b9b7494adeace1b88e7adfaecd7eeaa78b82e0fc83a75d20865","side":"right"},{"sibling":"b180cfc3f8638c912e90139ec42e2e3fd9b67b3fe342b36e8954314633ae5f61","side":"left"},{"sibling":"a4d17aefe58175050dc159af6246658fcf1c9f3ed57aacf1b350fc3261de4e69","side":"left"},{"sibling":"280b980aa0c7756b0b0cb22658f26466d36f0e70fbc3312cd2311d9898e30b8f","side":"right"},{"sibling":"c98954d4b658b1dda60fe52576fcf9bf21a2d49c67fb63f8c30f16ab5f721938","side":"right"},{"sibling":"cdb58f86163046d3b15f857b03372ec75e1ad9ea4548e086793d528b9eed364d","side":"left"},{"sibling":"533d82482604463aa4a281b9d8b85917b383b7c5f924b2b494039524c55e8797","side":"left"},{"sibling":"b2590791b920ca2a4ed39de126d2c0b1a10d9e7e62f572f12425f214e767b6e1","side":"left"},{"sibling":"6cea4964f32722eb370847c2f7c9d6a9f0622c239538b07e6815a59d6fd8d49c","side":"right"},{"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":228173,"merkle_root":"7e416202c0bfd759bd2eea4236713b403993d99793fe8badb5065040080bece3","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260611T143708Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-11T21:59:35Z","sig_algorithm":"ed25519","signature":"231c80024bc3982dd493c45b31af95097e97aabc6d712a4e5bad7d0cbdd3c08e01ff395b0f8e72754bac97016e0cd0eed88b8a13cb71edbbcb9b6d72c10a7b03","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_20b15dba8d2c77f4edb8eddbbd8914c47c3cc02286f499130ac8573ba30a7a4a"}}