{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RFC2MPHT7P5K5SQR4N7SYI4VDH","short_pith_number":"pith:RFC2MPHT","schema_version":"1.0","canonical_sha256":"8945a63cf3fbfaaeca11e37f2c239519d50f718d4098b71cdf45e2f5ea91fd40","source":{"kind":"arxiv","id":"2608.05519","version":1},"attestation_state":"computed","paper":{"title":"EcoAgent-Bench: Evaluating Economic Decision-Making in Budget-Constrained LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Feixiang Cheng, Jie Wu, Ming Gong, Qinqin Zhao","submitted_at":"2026-08-06T01:47:47Z","abstract_excerpt":"Agent benchmarks usually measure task completion and treat resource use as an auxiliary statistic. In deployment, however, the choice among a local lookup, broad search, composite research tool, stronger model, or human escalation is part of the task itself. We introduce EcoAgent-Bench, in which every task specifies priced actions and an explicit budget. Its 304 real-derived tasks span five families adapted from GAIA, HotpotQA, and MuSiQue, and test four decisions: avoiding unnecessary escalation, escalating when local evidence is insufficient, selecting a model tier, and stopping on unsupport"},"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":"2608.05519","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-06T01:47:47Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"9709416b4d84e8468bf0db38938ee162df775dec2e447e721e39510225585f06","abstract_canon_sha256":"12b9e28a68634138723a287689727998d0c76740a132187d908ccf78069c2eb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:48:00.803091Z","signature_b64":"vzrwyXqtWZzfy8mkoGFq749UzHAHEy752Pv5VHD1s8VXUYgjjP03KXiE7RKT6/W/831lyjP8T/0IpvxjwUe4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8945a63cf3fbfaaeca11e37f2c239519d50f718d4098b71cdf45e2f5ea91fd40","last_reissued_at":"2026-08-07T00:48:00.801644Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:48:00.801644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EcoAgent-Bench: Evaluating Economic Decision-Making in Budget-Constrained LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Feixiang Cheng, Jie Wu, Ming Gong, Qinqin Zhao","submitted_at":"2026-08-06T01:47:47Z","abstract_excerpt":"Agent benchmarks usually measure task completion and treat resource use as an auxiliary statistic. In deployment, however, the choice among a local lookup, broad search, composite research tool, stronger model, or human escalation is part of the task itself. We introduce EcoAgent-Bench, in which every task specifies priced actions and an explicit budget. Its 304 real-derived tasks span five families adapted from GAIA, HotpotQA, and MuSiQue, and test four decisions: avoiding unnecessary escalation, escalating when local evidence is insufficient, selecting a model tier, and stopping on unsupport"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05519","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/2608.05519/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":"2608.05519","created_at":"2026-08-07T00:48:00.803007+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05519v1","created_at":"2026-08-07T00:48:00.803007+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05519","created_at":"2026-08-07T00:48:00.803007+00:00"},{"alias_kind":"pith_short_12","alias_value":"RFC2MPHT7P5K","created_at":"2026-08-07T00:48:00.803007+00:00"},{"alias_kind":"pith_short_16","alias_value":"RFC2MPHT7P5K5SQR","created_at":"2026-08-07T00:48:00.803007+00:00"},{"alias_kind":"pith_short_8","alias_value":"RFC2MPHT","created_at":"2026-08-07T00:48:00.803007+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/RFC2MPHT7P5K5SQR4N7SYI4VDH","json":"https://pith.science/pith/RFC2MPHT7P5K5SQR4N7SYI4VDH.json","graph_json":"https://pith.science/api/pith-number/RFC2MPHT7P5K5SQR4N7SYI4VDH/graph.json","events_json":"https://pith.science/api/pith-number/RFC2MPHT7P5K5SQR4N7SYI4VDH/events.json","paper":"https://pith.science/paper/RFC2MPHT"},"agent_actions":{"view_html":"https://pith.science/pith/RFC2MPHT7P5K5SQR4N7SYI4VDH","download_json":"https://pith.science/pith/RFC2MPHT7P5K5SQR4N7SYI4VDH.json","view_paper":"https://pith.science/paper/RFC2MPHT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05519&json=true","fetch_graph":"https://pith.science/api/pith-number/RFC2MPHT7P5K5SQR4N7SYI4VDH/graph.json","fetch_events":"https://pith.science/api/pith-number/RFC2MPHT7P5K5SQR4N7SYI4VDH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RFC2MPHT7P5K5SQR4N7SYI4VDH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RFC2MPHT7P5K5SQR4N7SYI4VDH/action/storage_attestation","attest_author":"https://pith.science/pith/RFC2MPHT7P5K5SQR4N7SYI4VDH/action/author_attestation","sign_citation":"https://pith.science/pith/RFC2MPHT7P5K5SQR4N7SYI4VDH/action/citation_signature","submit_replication":"https://pith.science/pith/RFC2MPHT7P5K5SQR4N7SYI4VDH/action/replication_record"}},"created_at":"2026-08-07T00:48:00.803007+00:00","updated_at":"2026-08-07T00:48:00.803007+00:00"}