{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YV7G722P4I5GOX7G6V6SL622ZL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"83c7fdd7fb192ed4de5ff6c4700f3c35a5e5a0802110f1760e5609302563217b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-03T14:21:33Z","title_canon_sha256":"2b23e94220afe263eedd8fd666439a830bbd5de9a3b3dcb98801570016018462"},"schema_version":"1.0","source":{"id":"2504.02623","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02623","created_at":"2026-07-05T10:49:52Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02623v3","created_at":"2026-07-05T10:49:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02623","created_at":"2026-07-05T10:49:52Z"},{"alias_kind":"pith_short_12","alias_value":"YV7G722P4I5G","created_at":"2026-07-05T10:49:52Z"},{"alias_kind":"pith_short_16","alias_value":"YV7G722P4I5GOX7G","created_at":"2026-07-05T10:49:52Z"},{"alias_kind":"pith_short_8","alias_value":"YV7G722P","created_at":"2026-07-05T10:49:52Z"}],"graph_snapshots":[{"event_id":"sha256:bc663954c79cde648bb014b32f0165e86df2e6c45399ba8ffbb8f5d8ec44ad28","target":"graph","created_at":"2026-07-05T10:49:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.02623/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) demonstrate strong potential as agents for tool invocation due to their advanced comprehension and planning capabilities. Users increasingly rely on LLM-based agents to solve complex missions through iterative interactions. However, existing benchmarks predominantly access agents in single-mission scenarios, failing to capture real-world complexity. To bridge this gap, we propose the Multi-Mission Tool Bench. In the benchmark, each test case comprises multiple interrelated missions. This design requires agents to dynamically adapt to evolving demands. Moreover, the","authors_text":"Feng Zhang, Haorui Wang, Jinjian Li, Peijie Yu, Xiao Feng, Yifan Yang, Zelong Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-03T14:21:33Z","title":"Multi-Mission Tool Bench: Assessing the Robustness of LLM based Agents through Related and Dynamic Missions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02623","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:71f68b85a2caac5701b92a6033b6d188459bd2c516a6e7085dcb606cb842ab00","target":"record","created_at":"2026-07-05T10:49:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"83c7fdd7fb192ed4de5ff6c4700f3c35a5e5a0802110f1760e5609302563217b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-03T14:21:33Z","title_canon_sha256":"2b23e94220afe263eedd8fd666439a830bbd5de9a3b3dcb98801570016018462"},"schema_version":"1.0","source":{"id":"2504.02623","kind":"arxiv","version":3}},"canonical_sha256":"c57e6feb4fe23a675fe6f57d25fb5acaf7b018aa1444e33fda8b6a25d4521642","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c57e6feb4fe23a675fe6f57d25fb5acaf7b018aa1444e33fda8b6a25d4521642","first_computed_at":"2026-07-05T10:49:52.774077Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:52.774077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mQslRD8q9K7mXGA4M2mGv2r/qq/fF0LxiRZM/kIh58UPFJBFT7/t23HHKj/BUfMdfx0hjvGJby5IC666q+iaAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:52.774571Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.02623","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71f68b85a2caac5701b92a6033b6d188459bd2c516a6e7085dcb606cb842ab00","sha256:bc663954c79cde648bb014b32f0165e86df2e6c45399ba8ffbb8f5d8ec44ad28"],"state_sha256":"3469295bcf5ca4e8b21cccdd4167b0412358c8563cae27bb76933807dde8070d"}