{"_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_0255d412bd4b0268e1384d47006feb95019b2e4410efabe4fc72717d2be87e0d","bitcoin_anchor":{"bitcoin_attestations":["bitcoin_block_949451"],"calendar_attestations":["https://finney.calendar.eternitywall.com","https://btc.calendar.catallaxy.com","https://alice.btc.calendar.opentimestamps.org","https://bob.btc.calendar.opentimestamps.org"],"ots_url":"/registry/data/substrate/anchors/77fc9c28fae777b81da5b495b3115474df6592dfac590333213d3bdf8b94a9b3.ots","stamped_at":"2026-05-15T03:00:03Z","status":"bitcoin"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_0255d412bd4b0268e1384d47006feb95019b2e4410efabe4fc72717d2be87e0d","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"12273bd6d55b2f2639ea85c3f0007139168ed295e905fe25092f17515135792e","published":"Wed, 13 May 2026 00:00:00 -0400","receipt_hash":"12273bd6d55b2f2639ea85c3f0007139168ed295e905fe25092f17515135792e","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":"12273bd6d55b2f2639ea85c3f0007139168ed295e905fe25092f17515135792e","observed_at":"2026-05-13T04:43:23.245186Z","parent_run_hash":"2a6c2eea51fc0fdbbd1acb92c878f75767034fb102189f6a665cf0ad0e16536e","published":"Wed, 13 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:2605.08978v2 Announce Type: new \nAbstract: Recent advancements in agentic test-time scaling allow models to gather environmental feedback before committing to final actions. A key limitation of existing methods is that they typically employ undifferentiated exploration strategies, lacking the ability to adaptively distinguish when exploration is truly required. In this paper, we propose an exploration-aware reinforcement learning framework that enables LLM agents to adaptively explore only when uncertainty is high. Our method introduces a fine-grained reward function via variational inference that explicitly evaluates exploratory actions by estimating their potential to improve future decision-making, together with an exploration-aware grouping mechanism that separates exploratory actions from task-completion actions during optimization. By targeting informational gaps, this design allows agents to explore selectively and transition to execution as soon as the task context is cle","title":"Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization","url":"https://arxiv.org/abs/2605.08978","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.08978v2 Announce Type: new \nAbstract: Recent advancements in agentic test-time scaling allow models to gather environmental feedback before committing to final actions. A key limitation of existing methods is that they typically employ undifferentiated exploration strategies, lacking the ability to adaptively distinguish when exploration is truly required. In this paper, we propose an exploration-aware reinforcement learning framework that enables LLM agents to adaptively explore only when uncertainty is high. Our method introduces a fine-grained reward function via variational inference that explicitly evaluates exploratory actions by estimating their potential to improve future decision-making, together with an exploration-aware grouping mechanism that separates exploratory actions from task-completion actions during optimization. By targeting informational gaps, this design allows agents to explore selectively and transition to execution as soon as the task context is cle","title":"Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-13T04:43:23Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.08978"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:320a810042bb2589eef8e9f17a3c25540ed74d3fa5c72c92bb019361118b7626e61991d0d0d659cfb236a4f74c88c7bb810ad3c41b5821aaec02443a33bb5202","signer":"crovia.substrate","subject":{"observed_at":"2026-05-13T04:43:23Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.08978"},"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":"3a22fd33dafa8f52a78f7a3cace844cea6a0eef3e548efbd3382b5c62ee2298e","leaf_index":130813,"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":"84580b51487e39de61b569eb6290bdd692b96775abe4a084d6f8827966dd259a","side":"left"},{"sibling":"5697585ebd51afcfc98d4bec07b7c208eb152fa52b7f7c005b212e9aa9f22cba","side":"right"},{"sibling":"13ad7bfaad07783afc61018a8660dce8cd3556664d3d99c7feef59c15af34dc3","side":"left"},{"sibling":"f6224e3775d2e855dcdb06795c26a745ba9ed0ba0aa4197f29f63176d121e480","side":"left"},{"sibling":"faa9e662ca50aa2656dd62d1e5c3df1772b0a857ba20e5891611375d6ed10312","side":"left"},{"sibling":"5be85a2ca6238bc8d5b5474e4dd07027ad267209a1aa4ad4b415d197b1b1e18e","side":"left"},{"sibling":"e9c7d26c2fb7cdc9b4ec4b766fced88cdfef0a16254e8d6c349eefe592870c92","side":"left"},{"sibling":"7955fb5c18780780ebd0c129481f6b431d3c7bc9a5684bea51c4f13d54d0fd20","side":"left"},{"sibling":"2cdf0278f203c3924f9abe51f24da8450ad2d85d564d0c7ea68b368e28c336f4","side":"right"},{"sibling":"2170332c55df32c3e98553424d3e6242cef02b9714e5a34c7878ee7365425826","side":"left"},{"sibling":"ae6b2233fdba10d8b237d055d6febc6665ca818dcd31382efc2ab8723586948f","side":"left"},{"sibling":"d32d0a951c1d7e98a8e1951a587d83c97962daeeaa455643bc1d5d53744dc21e","side":"left"},{"sibling":"ffc4d51379293bc3e1910c7d612f409dc610fd9acf8241793fb89f82e1bad4ef","side":"left"},{"sibling":"62ac6554017807bd83187f5a3e5f4f72d6c482616429c2780e9fff1f4845fa04","side":"left"},{"sibling":"3a5e69cf0803f4c91f3895ed7c9a95748fef240bec4422e167c05300f79f06c0","side":"left"},{"sibling":"f2817ab288b5324fe49770372c7a10f33f7cd11005f8d4c0a730316f5229dc98","side":"left"},{"sibling":"725fac972e772ca0dc598810ea1abc70df472f72d2d6ab8a0baee2b80e5d2f4c","side":"left"},{"sibling":"98fc57dfef8873b512edc8340f7181df57302bb96777625e072235c62d7c5895","side":"right"}]},"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":134292,"merkle_root":"77fc9c28fae777b81da5b495b3115474df6592dfac590333213d3bdf8b94a9b3","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260515T023701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-15T02:37:25Z","sig_algorithm":"ed25519","signature":"68107a834b00b24f5d4501e5ec727445311f132a486567ecc4c72a4e6dff24c8c21f2de3105293353ba5fdbe370d032819af6aa70f694e2e39b6af6737507009","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_0255d412bd4b0268e1384d47006feb95019b2e4410efabe4fc72717d2be87e0d"}}