{"_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_ed3a959aeb9adb652d2504e117da2b57619ea711339c75f9c1c157bf34735d1a","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_ed3a959aeb9adb652d2504e117da2b57619ea711339c75f9c1c157bf34735d1a","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"21a048214b50782fed07be3082dd9c55e7f6aaa139deffa772644292ec49e4e5","published":"Thu, 28 May 2026 00:00:00 -0400","receipt_hash":"21a048214b50782fed07be3082dd9c55e7f6aaa139deffa772644292ec49e4e5","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":"21a048214b50782fed07be3082dd9c55e7f6aaa139deffa772644292ec49e4e5","observed_at":"2026-05-28T04:43:38.862500Z","parent_run_hash":"58f8b4a134069e0a15ea3949252489597eb86dd27c9ca3fb15c6fb838ce49ef3","published":"Thu, 28 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:2511.14584v3 Announce Type: replace-cross \nAbstract: We present ReflexGrad, a dual-process architecture for within-episode failure recovery in LLM agents without demonstrations. When agents commit to a wrong approach early and exhaust the step budget, the post-failure trajectory contains the information to escape -- but no published architecture acts on it within a single episode. ReflexGrad routes between a fast process (TextGrad-style continuous refinement every $k{=}3$ steps) and a slow process (Reflexion-style causal diagnosis when $m{=}5$ consecutive low-progress scores fire a routing gate). A deterministic priority merge keeps the natural-language policy coherent, and each slow activation emits three observable artifacts: a reproducible trigger, a causal diagnostic, and a verified fix. On ALFWorld 134 tasks, $n{=}10$ seeds, no demonstrations, ReflexGrad lifts Qwen-3-8B from $35.1\\%$ to $75.4\\%$ ($+40.3$pp), beating compute-matched 1-shot LATS by $+2.7$pp ($p{\\approx}0.01$),","title":"ReflexGrad: Within-Episode Failure Recovery in LLM Agents via Progress-Gated Dual-Process Routing","url":"https://arxiv.org/abs/2511.14584","vendor":"arxiv_cs_ai"},"summary":"arXiv:2511.14584v3 Announce Type: replace-cross \nAbstract: We present ReflexGrad, a dual-process architecture for within-episode failure recovery in LLM agents without demonstrations. When agents commit to a wrong approach early and exhaust the step budget, the post-failure trajectory contains the information to escape -- but no published architecture acts on it within a single episode. ReflexGrad routes between a fast process (TextGrad-style continuous refinement every $k{=}3$ steps) and a slow process (Reflexion-style causal diagnosis when $m{=}5$ consecutive low-progress scores fire a routing gate). A deterministic priority merge keeps the natural-language policy coherent, and each slow activation emits three observable artifacts: a reproducible trigger, a causal diagnostic, and a verified fix. On ALFWorld 134 tasks, $n{=}10$ seeds, no demonstrations, ReflexGrad lifts Qwen-3-8B from $35.1\\%$ to $75.4\\%$ ($+40.3$pp), beating compute-matched 1-shot LATS by $+2.7$pp ($p{\\approx}0.01$),","title":"ReflexGrad: Within-Episode Failure Recovery in LLM Agents via Progress-Gated Dual-Process Routing","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-28T04:43:38Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2511.14584"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:2f3cfec3b85b393cd3223ba81d7a4b114598e86b2701812e6bc5a3ab459fa400a10bafc53b0fcf976f3e6692272c8257d82255882171d82451dd0a15db914403","signer":"crovia.substrate","subject":{"observed_at":"2026-05-28T04:43:38Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2511.14584"},"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":"cb9401a3a2f49d72bb8ca57bce3d49b9d4d86899f7547bc3b53d6fcbd6a5254c","leaf_index":156026,"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":"7ec340e15d741c8f2ef0777065a36fe2f4b256096bfe80a11eb1de5b0ce82583","side":"right"},{"sibling":"d9b0ca502ec35a39c76db6199a1a43a6a9b6043e2fabd5e0f59978e951960daf","side":"left"},{"sibling":"d0a39303197195c6b87ba13fc152b8d097b008c7cee894acd6addba0b15eb786","side":"right"},{"sibling":"fcaae081a31d659939f1a485f08f16e38b23e4c3f8e261178f675f13a7c191ec","side":"left"},{"sibling":"0b5cf3f4a56dfa82a70c0f3a5da3633d09d392f570d3b8c6d427594da54ff7a6","side":"left"},{"sibling":"0e947bacca667a7e73b8b45520a9acad152f6e5e9f23285c3bade376803c9811","side":"left"},{"sibling":"b1cb4cc44838112bf6fe0f93a2f51f7910129f733310360c3ea15b88b277768f","side":"left"},{"sibling":"23dd40eb30de320ad1061f73adc18c4482f490a6bd28a6d2175e4ff59f041bbb","side":"right"},{"sibling":"92ebfba9adaa779ba57179e1e0f933c2128036a29e48cb81e4e64272dbbbb5c0","side":"left"},{"sibling":"f292d3278e493ec60902181b8c0bd5c89c0a1168ef928222fe6161287982f7f0","side":"right"},{"sibling":"2209295faf1a5bf51c97c6fd5a839a8181a4ea44f490420381530f35df7d9b2f","side":"right"},{"sibling":"5784576a15214ea9fc3569e6e1cff1ef443c0b1fc0d036028489088af089de27","side":"right"},{"sibling":"311772ec218efcb2da5a337f9e9f042fe1cc0028643adb0a354787e4ea7911b7","side":"right"},{"sibling":"66331bac84ca0f8983eb09fac7eaf95af234f1b82680b793eabff4ee25caac40","side":"left"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"7b6f0bea4291a5e63574dfca9aa0f9756f450c9478c3d07474d39a7ababb51f9","side":"right"},{"sibling":"1d39fe14b21e2ebbfb87e882423b24ee9469eae1e4c77af5b799ac4db9537467","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":156177,"merkle_root":"c5705a0243d16afd8b1ebfd731b7aa304079c442c2a7906493c5bbed374c69ec","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260528T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-28T05:37:36Z","sig_algorithm":"ed25519","signature":"f087e13febc8bb6a2e0812610de64cebc65be92915518d9c4b230799c3b161839b04c4eb1b02741f938f35545a76ab76555b04c782bdc2f9a44852d171d65909","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_ed3a959aeb9adb652d2504e117da2b57619ea711339c75f9c1c157bf34735d1a"}}