{"_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_486d1626d5f7d1b595cd09afa3de68a2a5a0c8ed2cdc474c0aca3332c53a63eb","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_486d1626d5f7d1b595cd09afa3de68a2a5a0c8ed2cdc474c0aca3332c53a63eb","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"6f9641440cae7f3006eee044b8d1a3855f8f47ff42d8d342e12cef17be2e0e36","published":"Thu, 09 Jul 2026 00:00:00 -0400","receipt_hash":"6f9641440cae7f3006eee044b8d1a3855f8f47ff42d8d342e12cef17be2e0e36","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":"6f9641440cae7f3006eee044b8d1a3855f8f47ff42d8d342e12cef17be2e0e36","observed_at":"2026-07-09T04:43:38.345231Z","parent_run_hash":"3e22c7c40abc4d94232acf1766a43492b8b8d51d10a58f1109535988a16554e6","published":"Thu, 09 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:2607.07508v1 Announce Type: cross \nAbstract: Reinforcement learning (RL) is becoming increasingly important for post-training large language models (LLMs). Previous RL pipelines for LLMs were mostly synchronous and batch-interleaved, which is inefficient for long-horizon agentic tasks. Recently, asynchronous RL has emerged as a more efficient alternative by updating the model as rollouts arrive. However, existing asynchronous RL systems often emphasize throughput, while leaving training stability and task effectiveness largely underexplored. For example, a key challenge is that group-wise sampling in the widely-used GRPO framework does not naturally fit asynchronous agentic training. In this paper, we present Single-rollout Asynchronous Optimization (SAO) to address the stability and off-policy challenges in asynchronous RL. To reduce off-policy effects and improve generalization, we replace group-wise sampling with single-rollout sampling, that is, using one rollout per prompt. ","title":"Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning","url":"https://arxiv.org/abs/2607.07508","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.07508v1 Announce Type: cross \nAbstract: Reinforcement learning (RL) is becoming increasingly important for post-training large language models (LLMs). Previous RL pipelines for LLMs were mostly synchronous and batch-interleaved, which is inefficient for long-horizon agentic tasks. Recently, asynchronous RL has emerged as a more efficient alternative by updating the model as rollouts arrive. However, existing asynchronous RL systems often emphasize throughput, while leaving training stability and task effectiveness largely underexplored. For example, a key challenge is that group-wise sampling in the widely-used GRPO framework does not naturally fit asynchronous agentic training. In this paper, we present Single-rollout Asynchronous Optimization (SAO) to address the stability and off-policy challenges in asynchronous RL. To reduce off-policy effects and improve generalization, we replace group-wise sampling with single-rollout sampling, that is, using one rollout per prompt. ","title":"Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-09T04:43:38Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.07508"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:2e481f2079d1d1a4796581d9b024110a4634ab1fea0b8a001d41bd92e65c63568f71f9fb453134bb47fec97a422be174cbf7791f78a88160fc5d9eef6bcb7309","signer":"crovia.substrate","subject":{"observed_at":"2026-07-09T04:43:38Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.07508"},"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":"edac9001d0a7451bb1b50517045e55109bccc72670fb6f296bc7e5fe62681a0b","leaf_index":296141,"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":"ee04390bc544ffa7ad511dc23725e378864e999d2f5bd6d34f7df9a90f38da9f","side":"left"},{"sibling":"0a0a4166d2e623fea09d557f8bcc4dd0c924068cd13c39b23fa9e0b958268f20","side":"right"},{"sibling":"0c6bb7e9d9201f6efe11cc38788c7ba267a60e209d8ba3b6f3808c51408dd27c","side":"left"},{"sibling":"c0371562f941f86120bf756778ce6b24ed62638eac4fe76309994ebf310498d0","side":"left"},{"sibling":"bc70e017fa120df50469b227034959f88f28d439e07823078b398491650775da","side":"right"},{"sibling":"c495f0db8a11947ce66c64465f632217620bdfc8ce3a8dd62c037e674b2ea376","side":"right"},{"sibling":"0c64b5ca40a519de00e7e467e1220b2def2b2b1f0826ffde72f1d615f3bcf094","side":"left"},{"sibling":"6e8f2e16cb75beb661e7f7b63be19804b6f6474dfbf899f8e417b19695f2fba4","side":"left"},{"sibling":"47a94dfb6e50a020e68582e6af2e6a8cf5a4c7efe9fed3deaedbc51f53d75367","side":"right"},{"sibling":"92bb57de69c78fd32ac7108b10d81676c184265a5a53de3c4b22d8cf3b54b499","side":"right"},{"sibling":"85a226efd14acc17835b04bc26706fa44595edbd531f194faf59f60ab72d4bb8","side":"left"},{"sibling":"da38b05536b12aee196b6ac988739211c257d32da790faccf5ac4b0cbc1bb15c","side":"right"},{"sibling":"d438dc3eddb0b14dc8b97cd021a4f44545ce5a8e827f3ea4044fd32b1877475e","side":"right"},{"sibling":"f73ad10346837ae47f59f0647f79b9416e1d499bf2b90af44448e7f09372200a","side":"right"},{"sibling":"bdc09902fcd434c0f7d3e680bf550e560777228c0b085ce80c637ce97fc4104c","side":"right"},{"sibling":"d8b9143917b539c543cf4448cec00131f8b807bd8004979c54ebe09798748c66","side":"left"},{"sibling":"ba603dffe985ef518e3a72793a3eaca83a7f1a79e5491fd0f62f421339f2d137","side":"right"},{"sibling":"be20b90931f0a14e3558ea4387537200fcbd14e019b3c5ed07a2ae4c62fc7c42","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":296360,"merkle_root":"64af62f723a5bc02adfa98b77e2006fc634de4ebf68626694f052342a200bea2","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260709T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-09T05:38:18Z","sig_algorithm":"ed25519","signature":"92ece7411e0d82898aac164e7d6573a6d0f7a595aad0780d710d873e548a061d2a8678cef4d237d3bf0eabe0a5f766b41cbc0b4bada2801e7532026291b4a309","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_486d1626d5f7d1b595cd09afa3de68a2a5a0c8ed2cdc474c0aca3332c53a63eb"}}