{"_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_c2987020ea026eb0fddd401ae2c4d6481de99435b15cd807d21280b2d285768e","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_c2987020ea026eb0fddd401ae2c4d6481de99435b15cd807d21280b2d285768e","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"f5fa4ea43abbcf774f964f1ea6ddceab4527bb489d79dc8083c9c7cf64495c89","published":"Mon, 01 Jun 2026 00:00:00 -0400","receipt_hash":"f5fa4ea43abbcf774f964f1ea6ddceab4527bb489d79dc8083c9c7cf64495c89","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":"f5fa4ea43abbcf774f964f1ea6ddceab4527bb489d79dc8083c9c7cf64495c89","observed_at":"2026-06-01T04:43:13.859018Z","parent_run_hash":"8993bbc535dae8c9669e099af3624cb39166b8d9bbfd66f26ae5c338cbb21be2","published":"Mon, 01 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:2605.30738v1 Announce Type: new \nAbstract: Generalization across agentic tool-calling environments remains a central challenge for reliable agentic reasoning systems. Although large language models achieve strong results on individual benchmarks, their ability to compose reasoning strategies, preserve intermediate states, and coordinate tools across domains remains underexplored. We present MAVEN (Modular Agentic Verification and Execution Network), a lightweight symbolic reasoning scaffold for structured decomposition, adaptive tool orchestration, and intermediate verification. We evaluate MAVEN across established tool-calling benchmarks, including BFCL v3, TauBench, Tau2Bench, AceBench, and introduce MAVEN-Bench, a stress-test benchmark for multi-step mathematical and physical reasoning with explicit verification and adversarial task composition. MAVEN-Bench exposes a substantial gap between partial reasoning quality and end-to-end task success; in direct MAVEN-Bench runs, MAVE","title":"MAVEN: Improving Generalization in Agentic Tool Calling","url":"https://arxiv.org/abs/2605.30738","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.30738v1 Announce Type: new \nAbstract: Generalization across agentic tool-calling environments remains a central challenge for reliable agentic reasoning systems. Although large language models achieve strong results on individual benchmarks, their ability to compose reasoning strategies, preserve intermediate states, and coordinate tools across domains remains underexplored. We present MAVEN (Modular Agentic Verification and Execution Network), a lightweight symbolic reasoning scaffold for structured decomposition, adaptive tool orchestration, and intermediate verification. We evaluate MAVEN across established tool-calling benchmarks, including BFCL v3, TauBench, Tau2Bench, AceBench, and introduce MAVEN-Bench, a stress-test benchmark for multi-step mathematical and physical reasoning with explicit verification and adversarial task composition. MAVEN-Bench exposes a substantial gap between partial reasoning quality and end-to-end task success; in direct MAVEN-Bench runs, MAVE","title":"MAVEN: Improving Generalization in Agentic Tool Calling","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-01T04:43:13Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.30738"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:d4a11882bced9dfd996a42e923e932201ab6b6b085206d73b0528fd6f7f82d50f391f1dce051f4f5b4b7c9e46c3a8b4ae0d1794422dbf659b892bcc07b57e30b","signer":"crovia.substrate","subject":{"observed_at":"2026-06-01T04:43:13Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.30738"},"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":"2f08f6a94ddd6f7096a487320c0b23fa05231f458076bc6cee655dadf76471ac","leaf_index":163774,"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":"2e60e575a88b8fc7d95640320eceb3a956acfdfe3a69444c4c385bc150fdd94f","side":"right"},{"sibling":"9b9101ff16a09d81db2311de2d8c302e38865f43fa6ebceaa10035503b12436e","side":"left"},{"sibling":"0ae4b8d4efdd3acb849713bfc0ec21163751578185727496e5e5547e12f99dec","side":"left"},{"sibling":"2a0fa6eaa53bac91130d53faf37fd09c0b3fad962ae4839c3b4361a15252472d","side":"left"},{"sibling":"c584ac900eb00ae6df8f28f6414b3f34b2ec4175f422f070ffa8d1f10a753f15","side":"left"},{"sibling":"cf81c7f2db0ba0bfd8183af4b0ae1bdc1ca2f1ca46cb4985f1a47b0522b2393f","side":"left"},{"sibling":"c4c2af2c3e0b619e51f5245139abd800e86ff2d985c322e93bedf0607fe5c370","side":"right"},{"sibling":"764e4312cdb701ef8613acdc2311e1724d6a379f21c70c30ed832e7ede3d2d33","side":"left"},{"sibling":"5a0517e6c348bc5a70f1aef04c1415d23980c712e375838fff54dfa281f98760","side":"left"},{"sibling":"d6986f4b6a5bd07cba1de43f660d527af780ad1465d0f4af5f137bd514e95f7e","side":"left"},{"sibling":"aff54f89d4445cf32bb05b2ece532d190200cb92524489ddfa648b5cc36e21a4","side":"left"},{"sibling":"f028fad1771bff7dceff3a83baf90249f4eb410ebedfe92dda1bb2b89d7093c8","side":"left"},{"sibling":"59c6490072e8a1d357ece10bb08d7f449a3acbae58e130e3e7469cbea0314c65","side":"left"},{"sibling":"66331bac84ca0f8983eb09fac7eaf95af234f1b82680b793eabff4ee25caac40","side":"left"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"c9ac00eed8c475f1e525869bb329af03d052181b19ff8234edefe12f6ecec154","side":"right"},{"sibling":"ce41d9b82f34b16efd653dfb3552acc4e2512939e47903e5fc979fbed00c5764","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":164217,"merkle_root":"a1098816aea1b60b8fe37b62410469bc5024a2c335bbec4f6ef2add7875dbdf2","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260601T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-01T05:37:41Z","sig_algorithm":"ed25519","signature":"d7f91db1d54b9495c499440c2828f4bd53360555391ce6e25adea5183bc1fa0f697d80708a099d0b0429e6f8cb6c71e7fccf82acb3c84481149974fb26074708","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_c2987020ea026eb0fddd401ae2c4d6481de99435b15cd807d21280b2d285768e"}}