{"_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_290e5ea5b8017d94651f7affb663d51f4fa11bea0d2c7ff8b532991d399ecf11","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_290e5ea5b8017d94651f7affb663d51f4fa11bea0d2c7ff8b532991d399ecf11","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"4cf0dd1b24d1c7c1a00c0cc1f60af8a0797ab68620255fd08686161515fe8270","published":"Tue, 07 Jul 2026 00:00:00 -0400","receipt_hash":"4cf0dd1b24d1c7c1a00c0cc1f60af8a0797ab68620255fd08686161515fe8270","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":"4cf0dd1b24d1c7c1a00c0cc1f60af8a0797ab68620255fd08686161515fe8270","observed_at":"2026-07-07T04:43:08.294902Z","parent_run_hash":"fc40a96e5d33ecc82922806c3ad18de4725d7af03964570396c8af4e48fb5bc1","published":"Tue, 07 Jul 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:2602.21534v3 Announce Type: replace \nAbstract: Agentic reinforcement learning (ARL) has rapidly gained attention as a promising paradigm for training agents to solve complex, multi-step interactive tasks. Despite encouraging early results, ARL remains highly unstable, often leading to training collapse. This instability limits scalability to larger environments and longer interaction horizons, and constrains systematic exploration of algorithmic design choices. In this paper, we first propose ARLArena, a stable training recipe and systematic analysis framework that examines training stability in a controlled and reproducible setting. ARLArena first constructs a clean and standardized testbed. Then, we decompose policy gradient into four core design dimensions and assess the performance and stability of each dimension. Through this fine-grained analysis, we distill a unified perspective on ARL and propose SAMPO, a stable agentic policy optimization method designed to mitigate the ","title":"ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning","url":"https://arxiv.org/abs/2602.21534","vendor":"arxiv_cs_ai"},"summary":"arXiv:2602.21534v3 Announce Type: replace \nAbstract: Agentic reinforcement learning (ARL) has rapidly gained attention as a promising paradigm for training agents to solve complex, multi-step interactive tasks. Despite encouraging early results, ARL remains highly unstable, often leading to training collapse. This instability limits scalability to larger environments and longer interaction horizons, and constrains systematic exploration of algorithmic design choices. In this paper, we first propose ARLArena, a stable training recipe and systematic analysis framework that examines training stability in a controlled and reproducible setting. ARLArena first constructs a clean and standardized testbed. Then, we decompose policy gradient into four core design dimensions and assess the performance and stability of each dimension. Through this fine-grained analysis, we distill a unified perspective on ARL and propose SAMPO, a stable agentic policy optimization method designed to mitigate the ","title":"ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-07T04:43:08Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2602.21534"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:a40910dae497877ab90e74e401d6b7291f5e4c3bb4116644a2a269580c7011f56501f2e730431638fb10fa2e933fa1cb9863eba885ca24b75cec07ff9f532606","signer":"crovia.substrate","subject":{"observed_at":"2026-07-07T04:43:08Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2602.21534"},"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":"b2d63ec2cc023b298809512e2ea19178d7daa01887434eb377b9ed09312d4b2b","leaf_index":289185,"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":"2ceb0f70047a19361f265c7c9d0f3262eb7e81480c027b19c874dfec92ea8256","side":"left"},{"sibling":"0bc9f050d910c60bbb3b76626dcddfa119d35bed3ad0e62926950836f96ed233","side":"right"},{"sibling":"2d884289112b218c5537ac7afd1d5f49799d806e7921063c09199658740cfc0a","side":"right"},{"sibling":"6467aaca18e836f6b20ecef59d4da73e6dd7e0eac7947ba10763310e8a3f7c21","side":"right"},{"sibling":"1939c9419c806db0c67c2d8d044aca1ef15a904022d0c79cbae8a195c3a82ea1","side":"right"},{"sibling":"025c3b9f4a4cca084fa1decb74f05d27a5fe8fb4a58c38660223f457a060650a","side":"left"},{"sibling":"cfebf4e758f80b6c0a2520ffba9d9d900a232da3623a4c530a1c712d33cffc24","side":"right"},{"sibling":"a6e115fb6d42f8f126d042702270c371c7df6161120ef9b37366edddc165bd28","side":"left"},{"sibling":"35d3e8088ee93171aa479055dcd001cfb6d23925114ddc0908531e54298b0d29","side":"left"},{"sibling":"841129c21a7583176cdc7de281cadfe0e00d04673461e199760cd5128d8cc2d5","side":"right"},{"sibling":"19d6dfd29bc47f35fa02e8fe765277ba9cc3e6da5072309f24ebaac5b5f295e3","side":"right"},{"sibling":"8e0ad7889eb2d4b40e5b6c3d8e2eb19d4e202374983f468aa76321823de07a9f","side":"left"},{"sibling":"aae716235efcb893a1f219dbcd5095070d08a497769fc6d50c14976aa26d5750","side":"right"},{"sibling":"a75ab4319e241beeddb1b3f5705febe0422937926c3479923ccfb0b0082fa4e3","side":"left"},{"sibling":"bd04fa605f883bfb2b81510d045b1e85e555a03da3be083619f61384dfe40ff8","side":"left"},{"sibling":"1b72ad8d12164fdf329e7871711be99d8569d140b21f94056e6962da21da9ce1","side":"right"},{"sibling":"5f5109c2bfdcc7a7e70554bba25862e2d7ce86b6b0cd48a72eb66d2eb735f321","side":"right"},{"sibling":"05fd8a05dddb2e7f72bbb5b290ca55c378f1aed709f132277908d9a5f30eb605","side":"right"},{"sibling":"1cecb7f447febd025aac272837c80de218aecc6485d2395a509b2a1f1b9c746e","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":289613,"merkle_root":"dc428b9d9ba248d4f93f63147bf7c700bf5be7f500cec6c3507b9df6e9401601","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260707T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-07T05:38:15Z","sig_algorithm":"ed25519","signature":"c468b0e183383ab71992be40bda451093e6cd8cd8efb0d26f68e135a804b287c209d12a0f4fdd95c69c835c04b78df8cb1903dee1f53d4730b36f5332a29fe05","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_290e5ea5b8017d94651f7affb663d51f4fa11bea0d2c7ff8b532991d399ecf11"}}