{"_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_816eb1a41827eea9bc451520035e96b6b76fd5d2db4276fb31448b985d53e5e6","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_816eb1a41827eea9bc451520035e96b6b76fd5d2db4276fb31448b985d53e5e6","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"ccf3698bb8e46fbbc6b77b1f205e69a806d61a9af7fef23cebe00648ff97c340","published":"Mon, 25 May 2026 00:00:00 -0400","receipt_hash":"ccf3698bb8e46fbbc6b77b1f205e69a806d61a9af7fef23cebe00648ff97c340","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":"ccf3698bb8e46fbbc6b77b1f205e69a806d61a9af7fef23cebe00648ff97c340","observed_at":"2026-05-25T04:43:48.841018Z","parent_run_hash":"56713422f06ad87427cd8cdcdb1ed341feb016b33c37198d9b168328d1df15fb","published":"Mon, 25 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:2601.03715v2 Announce Type: replace-cross \nAbstract: Reinforcement learning drives recent advances in LLM reasoning and agentic capabilities, yet current approaches struggle with both exploration and exploitation. Exploration suffers from low success rates on difficult tasks and high costs of repeated rollouts from scratch. Exploitation suffers from coarse credit assignment and training instability: Trajectory-level rewards penalize valid prefixes for later errors, and failure-dominated groups overwhelm the few positive signals, leaving optimization without constructive direction. To this end, we propose R$^3$L, Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification. To synthesize high-quality trajectories, R$^3$L shifts from stochastic sampling to active synthesis via reflect-then-retry, leveraging language feedback to diagnose errors, transform failed attempts into successful ones, and reduce rollout costs by resta","title":"R$^3$L: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification","url":"https://arxiv.org/abs/2601.03715","vendor":"arxiv_cs_ai"},"summary":"arXiv:2601.03715v2 Announce Type: replace-cross \nAbstract: Reinforcement learning drives recent advances in LLM reasoning and agentic capabilities, yet current approaches struggle with both exploration and exploitation. Exploration suffers from low success rates on difficult tasks and high costs of repeated rollouts from scratch. Exploitation suffers from coarse credit assignment and training instability: Trajectory-level rewards penalize valid prefixes for later errors, and failure-dominated groups overwhelm the few positive signals, leaving optimization without constructive direction. To this end, we propose R$^3$L, Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification. To synthesize high-quality trajectories, R$^3$L shifts from stochastic sampling to active synthesis via reflect-then-retry, leveraging language feedback to diagnose errors, transform failed attempts into successful ones, and reduce rollout costs by resta","title":"R$^3$L: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-25T04:43:48Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2601.03715"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:e00a65e0999bb7654f58dd4038d6e06279ff63f47f921a87dfe26c2bbdcda5191184f4756dbde7baa2ed62bc0c3b9f14af8e1445f83eb0965aecd62f534bcb01","signer":"crovia.substrate","subject":{"observed_at":"2026-05-25T04:43:48Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2601.03715"},"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":"76e781f407bc44c720975f4bb4fa249f1c3ce2e5334a8d697ccaad9865f95155","leaf_index":149719,"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":"908cbb19d9b9c53cece2b901188c4f5dc5c79600807cf90e9206337a75b8b2f3","side":"left"},{"sibling":"fc260fbd0f91d93f878cb70a2e3f07f5537442ab7c298b7448a698347fb8f9a4","side":"left"},{"sibling":"db6b5fdce0e476cd4f8f68e12a05b81b494d98dced46d7262368ecf7cfcdd271","side":"left"},{"sibling":"ff3a8a5760373d38c65db26727a8e8c3e13444eb26f295caa23d47781b7855ff","side":"right"},{"sibling":"f37ede63d69322e373080e08eec32185e5627db081893f5e7c4dbaffde7d6166","side":"left"},{"sibling":"71332b767201373a22f07734e56c280aca2f5c4843249e6b798501f1aaebcd42","side":"right"},{"sibling":"9a9dec70c246f07136fd93efad0647d42e469fcfca31c6741dcb1d715bd9ce45","side":"left"},{"sibling":"cb71a04113e54ec457f452a34b2778696e1747afe98ba9da255ce1f5fd8619d7","side":"left"},{"sibling":"e044acc52c31efe134c902c984299ea3452b42df993d096ed61ad8be9d530bbc","side":"right"},{"sibling":"6be461ecf12dedf98a31921aa7b5c32d4a32df6897e0f697b8bf1a4ba3e2d324","side":"right"},{"sibling":"c2861a8cef3eb66bf2726aa377c24a6bf6e8b7489dcd0e870b61d62a35ccadfb","side":"right"},{"sibling":"134949308b15cffd6792ee2cf678119af34d69a64764d7c89cd47573c94e1cda","side":"left"},{"sibling":"debbc1a6232ea7970009b91bdc2345041b2de5ac59551f955855d579001e512c","side":"right"},{"sibling":"216869846f40bd905626884f58cb67b9019e488b3656946a7808c436ab7339ac","side":"right"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"e734b0c6d6d13acb5f4cf00367b3913e5bbf1aa717377aa4e4820c6de24b7673","side":"right"},{"sibling":"4bbb7f78e96179bb9cdd06d7207b66b3503ab68e4880438263025b04ebe8f7ec","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":149835,"merkle_root":"51484a548bc0cf3d178eec868e98935c87f0aa83369143b7c96b048585e5ba01","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260525T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-25T05:37:33Z","sig_algorithm":"ed25519","signature":"99a657e53a015ace0bade5d7fbb3f60f950b6d1e1128251a63afcc454a492422cae5efdc0c18503b4f7e62f371bd48f2889be78d9048c4681d6c1e73f754d705","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_816eb1a41827eea9bc451520035e96b6b76fd5d2db4276fb31448b985d53e5e6"}}