{"_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_6e70c82847fbcc42a2180ab4e914029e3085dda6ab88f8d08e9127ceb4a4c8a5","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_6e70c82847fbcc42a2180ab4e914029e3085dda6ab88f8d08e9127ceb4a4c8a5","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"de689563d316d3a7794a14b0d86e1181846a88d4e2432928fa896bae59b2eaee","published":"Wed, 03 Jun 2026 00:00:00 -0400","receipt_hash":"de689563d316d3a7794a14b0d86e1181846a88d4e2432928fa896bae59b2eaee","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":"de689563d316d3a7794a14b0d86e1181846a88d4e2432928fa896bae59b2eaee","observed_at":"2026-06-03T04:43:57.136784Z","parent_run_hash":"62ae9c8eda846b00bc49666345b338d00756c5203438666c4c1fc694cc364b84","published":"Wed, 03 Jun 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:2606.03077v1 Announce Type: cross \nAbstract: Reinforcement learning (RL) has become a standard post-training paradigm for large language models (LLMs), extending beyond preference alignment to complex reasoning and multi-turn agentic behaviors. In agentic RL, the rollout stage generates trajectories while invoking tools, producing long-tailed and non-stationary workloads that challenge conventional resource-management assumptions. Three fundamental challenges arise. First, due to the long-tail distribution, a small fraction of trajectories dominates rollout makespan. Second, rollout and training exhibit strong asymmetry in compute patterns, memory demands, and sensitivity to sequence length. Third, as the RL policy evolves, the trajectory-length distribution drifts over time, rendering any static resource split progressively suboptimal.\n  We present Libra, which introduces two core mechanisms. The first is a periodic global resource planner that jointly optimizes GPU allocation a","title":"Libra: Efficient Resource Management for Agentic RL Post-Training","url":"https://arxiv.org/abs/2606.03077","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.03077v1 Announce Type: cross \nAbstract: Reinforcement learning (RL) has become a standard post-training paradigm for large language models (LLMs), extending beyond preference alignment to complex reasoning and multi-turn agentic behaviors. In agentic RL, the rollout stage generates trajectories while invoking tools, producing long-tailed and non-stationary workloads that challenge conventional resource-management assumptions. Three fundamental challenges arise. First, due to the long-tail distribution, a small fraction of trajectories dominates rollout makespan. Second, rollout and training exhibit strong asymmetry in compute patterns, memory demands, and sensitivity to sequence length. Third, as the RL policy evolves, the trajectory-length distribution drifts over time, rendering any static resource split progressively suboptimal.\n  We present Libra, which introduces two core mechanisms. The first is a periodic global resource planner that jointly optimizes GPU allocation a","title":"Libra: Efficient Resource Management for Agentic RL Post-Training","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-03T04:43:57Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.03077"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:50b25a380ce8574fcc35295b1d6811962b43d0edae2f5487bf4ad930dc46d6bb7d9b93994803c160615ddafbd43341fea252fb34315d394323869ecf4cf88001","signer":"crovia.substrate","subject":{"observed_at":"2026-06-03T04:43:57Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.03077"},"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":"0c8fce358db8e0869cf4e08d2f1133b243ec46780e051a1348a76b6b1cb065c6","leaf_index":209176,"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":"abf49b02dc6e586e221abc4d414626318881420b5f675eb30c14c9e3895186b2","side":"right"},{"sibling":"0edca068121d812b65f92745bf4a4f2a80cd9871f3c50b73062f707dcd63b0ed","side":"right"},{"sibling":"c36c0aa76d23f5f3ce0036af5ad6b0b0f119fe01c7a408886c765d7e5ac677a3","side":"right"},{"sibling":"7bfda38f7ea93a1ae56fe629cc681c4d736c00c89d431bad9963f39558a4c430","side":"left"},{"sibling":"74d1c10d867c4b4222c71d5fca772d14a10866c914d0e683e9b72e04766a935b","side":"left"},{"sibling":"68367bd536b7ecea1c64d5778ff5f62698b49f3ad5fca28778be71045b3b8202","side":"right"},{"sibling":"40052708582da742bf088b0c30cd584ba95f867aa32f06040dcfa4b5df18f737","side":"right"},{"sibling":"2ef1f1a576d002b7a433f7807e3e3de79248e5d1145c4394fef6eb45b8063603","side":"right"},{"sibling":"2b9867040ec52d22722edc26b204e15651723dcc66d361cc1af11490a854d461","side":"left"},{"sibling":"2abcec6d14b256f82b270a3141886de6129141dec525543607b760f02588a877","side":"right"},{"sibling":"2b6b45743f97ac502854e489ac38a3366f8ae7ede58a2728b45daadbf29e9d03","side":"right"},{"sibling":"a81babbd79ea0da9e030dd7f43bffb6519d214317decd50727bea4e78189d970","side":"right"},{"sibling":"2dca509b3eb767a47cf215d4315f230ce9103a76264412008ae23a349b519ef1","side":"left"},{"sibling":"24d1bb4b13e0e46131b27b70a48e65fcf4e2e14b95e3bb83ade821e9df530f6b","side":"left"},{"sibling":"8d3baa674a45fd8bc6d3e8d25298f4bec86c72fa8259d576c330d12955c7b4f7","side":"right"},{"sibling":"e32819d1eff909db08066d1703f2db3f091cddac19378b2c0c625ab11e3fdbc0","side":"right"},{"sibling":"c300cf0154c136afc09b1702a0be98f4ba5b6dc5cf57e8cc714ec1eaf4196eff","side":"left"},{"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":209569,"merkle_root":"c852efc8ad7dfffc196c71380f79e6398bcaf566974cbae7c9950b0f600d5bc8","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260603T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-03T05:37:57Z","sig_algorithm":"ed25519","signature":"1ca417607effc813341721cfdade0a2d2d4ba96a90d361dbc3e864b6991b90abc326ec41d9ba3e7110cc04adb29d7b8d95abea7ff2ab8c591b2f864ed7270c03","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_6e70c82847fbcc42a2180ab4e914029e3085dda6ab88f8d08e9127ceb4a4c8a5"}}