{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NDFKPE52RV6JZRG6HD3V3RANVP","short_pith_number":"pith:NDFKPE52","schema_version":"1.0","canonical_sha256":"68caa793ba8d7c9cc4de38f75dc40dabc65a0d7107def69853cca9aeb7e61062","source":{"kind":"arxiv","id":"2607.23722","version":1},"attestation_state":"computed","paper":{"title":"E-Bench: Benchmarking Multi-Step Tool-Use Agents in Real-World Product Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alphet Liu, Duran Zheng, Eileen Ye, Maxm Pan, Tianyuan Zou, Weihuang Zheng, Ya-Qin Zhang, Youyong Kong","submitted_at":"2026-07-26T15:38:28Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly deployed as agents that interact with stateful environments over multiple steps: gathering hidden information, composing tool calls, and committing state changes. We refer to this capability as multi-step tool use. Existing benchmarks have advanced tool-use agent evaluation, but often focus on isolated API calls, short trajectories, or settings that are difficult to scale or control. We introduce E-Bench, a fully synthetic benchmark with 323 state-changing tasks across three product domains: Honor of Kings, QQ Music, and Tencent Meeting. E-Bench de"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.23722","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-26T15:38:28Z","cross_cats_sorted":[],"title_canon_sha256":"942dd601f5a3f8976e5af368845d7bcee21f1b58c73a1d8f801513595e2fb46d","abstract_canon_sha256":"65ad11901142434fba9690b8c6467404f24b12d898eb0629b77fcc4b4ddf028e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:07.628504Z","signature_b64":"NZyLRrhL8dY4tPcL8UzswS5sbVgePpK/RKWcHSZrtKcjOx7IVRn14vIgCOW5QdNpQTRJV7UR9cRBYlJE6BWoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68caa793ba8d7c9cc4de38f75dc40dabc65a0d7107def69853cca9aeb7e61062","last_reissued_at":"2026-07-28T01:23:07.627642Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:07.627642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"E-Bench: Benchmarking Multi-Step Tool-Use Agents in Real-World Product Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alphet Liu, Duran Zheng, Eileen Ye, Maxm Pan, Tianyuan Zou, Weihuang Zheng, Ya-Qin Zhang, Youyong Kong","submitted_at":"2026-07-26T15:38:28Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly deployed as agents that interact with stateful environments over multiple steps: gathering hidden information, composing tool calls, and committing state changes. We refer to this capability as multi-step tool use. Existing benchmarks have advanced tool-use agent evaluation, but often focus on isolated API calls, short trajectories, or settings that are difficult to scale or control. We introduce E-Bench, a fully synthetic benchmark with 323 state-changing tasks across three product domains: Honor of Kings, QQ Music, and Tencent Meeting. E-Bench de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23722","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.23722/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.23722","created_at":"2026-07-28T01:23:07.628088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.23722v1","created_at":"2026-07-28T01:23:07.628088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23722","created_at":"2026-07-28T01:23:07.628088+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDFKPE52RV6J","created_at":"2026-07-28T01:23:07.628088+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDFKPE52RV6JZRG6","created_at":"2026-07-28T01:23:07.628088+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDFKPE52","created_at":"2026-07-28T01:23:07.628088+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NDFKPE52RV6JZRG6HD3V3RANVP","json":"https://pith.science/pith/NDFKPE52RV6JZRG6HD3V3RANVP.json","graph_json":"https://pith.science/api/pith-number/NDFKPE52RV6JZRG6HD3V3RANVP/graph.json","events_json":"https://pith.science/api/pith-number/NDFKPE52RV6JZRG6HD3V3RANVP/events.json","paper":"https://pith.science/paper/NDFKPE52"},"agent_actions":{"view_html":"https://pith.science/pith/NDFKPE52RV6JZRG6HD3V3RANVP","download_json":"https://pith.science/pith/NDFKPE52RV6JZRG6HD3V3RANVP.json","view_paper":"https://pith.science/paper/NDFKPE52","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.23722&json=true","fetch_graph":"https://pith.science/api/pith-number/NDFKPE52RV6JZRG6HD3V3RANVP/graph.json","fetch_events":"https://pith.science/api/pith-number/NDFKPE52RV6JZRG6HD3V3RANVP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDFKPE52RV6JZRG6HD3V3RANVP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDFKPE52RV6JZRG6HD3V3RANVP/action/storage_attestation","attest_author":"https://pith.science/pith/NDFKPE52RV6JZRG6HD3V3RANVP/action/author_attestation","sign_citation":"https://pith.science/pith/NDFKPE52RV6JZRG6HD3V3RANVP/action/citation_signature","submit_replication":"https://pith.science/pith/NDFKPE52RV6JZRG6HD3V3RANVP/action/replication_record"}},"created_at":"2026-07-28T01:23:07.628088+00:00","updated_at":"2026-07-28T01:23:07.628088+00:00"}