{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IGPFAYCXFTYJWAYOSLHXOQ4TAP","short_pith_number":"pith:IGPFAYCX","schema_version":"1.0","canonical_sha256":"419e5060572cf09b030e92cf77439303ed3a8dde833cd41f12183ab4a2884b89","source":{"kind":"arxiv","id":"2602.16246","version":3},"attestation_state":"computed","paper":{"title":"Toward Scalable Verifiable Reward: Proxy State-Based Evaluation for Multi-turn Tool-Calling LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Proxy state-based evaluation replaces costly deterministic backends with LLM trackers and judges for benchmarking multi-turn tool-calling agents.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alec Chiu, Avinash Thangali, Chaitanya Kulkarni, Linsey Pang, Prakhar Mehrotra, Shivani Shekhar, Uma Kona, Yirou Ge, Yixi Li, Yun-Shiuan Chuang, Zijie Pan","submitted_at":"2026-02-18T07:49:47Z","abstract_excerpt":"Interactive large language model (LLM) agents operating via multi-turn dialogue and multi-step tool calling are increasingly used in production. Benchmarks for these agents must both reliably compare models and yield on-policy training data. Prior agentic benchmarks, such as tau-bench, tau^2-bench, and AppWorld, rely on fully deterministic backends, which are costly to build and iterate. We propose Proxy State-Based Evaluation, an LLM-driven simulation framework that preserves final state-based evaluation without a deterministic database. Specifically, a scenario specifies the user goal, user/"},"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":true},"canonical_record":{"source":{"id":"2602.16246","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-18T07:49:47Z","cross_cats_sorted":[],"title_canon_sha256":"635d77fbd1eda53c4cd6f4a49799b35c1f57cb644153e4e92193aa1e23a02da9","abstract_canon_sha256":"3122410118920069546efceb4c409f16fc4600b24e7703a8fdcb3fc53e8ff3f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:31.143835Z","signature_b64":"HFJQtDPPS7c+Sm+S1YYUDRORrVefBlxLBMirhPIIoWI2LcchUtRsa5TD761RA4XUdmfdr2VxxDV/iym1FoBXBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"419e5060572cf09b030e92cf77439303ed3a8dde833cd41f12183ab4a2884b89","last_reissued_at":"2026-05-18T02:44:31.143396Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:31.143396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Scalable Verifiable Reward: Proxy State-Based Evaluation for Multi-turn Tool-Calling LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Proxy state-based evaluation replaces costly deterministic backends with LLM trackers and judges for benchmarking multi-turn tool-calling agents.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alec Chiu, Avinash Thangali, Chaitanya Kulkarni, Linsey Pang, Prakhar Mehrotra, Shivani Shekhar, Uma Kona, Yirou Ge, Yixi Li, Yun-Shiuan Chuang, Zijie Pan","submitted_at":"2026-02-18T07:49:47Z","abstract_excerpt":"Interactive large language model (LLM) agents operating via multi-turn dialogue and multi-step tool calling are increasingly used in production. Benchmarks for these agents must both reliably compare models and yield on-policy training data. Prior agentic benchmarks, such as tau-bench, tau^2-bench, and AppWorld, rely on fully deterministic backends, which are costly to build and iterate. We propose Proxy State-Based Evaluation, an LLM-driven simulation framework that preserves final state-based evaluation without a deterministic database. Specifically, a scenario specifies the user goal, user/"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Proxy state-based evaluation offers a practical, scalable alternative to deterministic agentic benchmarks for industrial LLM agents, producing stable model-differentiating rankings and on-/off-policy supervision that transfers to unseen scenarios.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That LLM state trackers and judges, when given carefully specified scenarios, can infer accurate proxy states and verify goal completion with near-zero hallucination rates and high reliability.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Introduces Proxy State-Based Evaluation as a scalable LLM-based method for verifiable assessment of multi-turn tool-calling agents using proxy states inferred from interaction traces.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Proxy state-based evaluation replaces costly deterministic backends with LLM trackers and judges for benchmarking multi-turn tool-calling agents.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"286af90951987f52f1120a23f176b998232573cdf0375274e7c2e03f731d5e4d"},"source":{"id":"2602.16246","kind":"arxiv","version":3},"verdict":{"id":"8a08f2dd-1f4c-4ad6-ae6b-6b020ed52f0f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T21:40:51.673070Z","strongest_claim":"Proxy state-based evaluation offers a practical, scalable alternative to deterministic agentic benchmarks for industrial LLM agents, producing stable model-differentiating rankings and on-/off-policy supervision that transfers to unseen scenarios.","one_line_summary":"Introduces Proxy State-Based Evaluation as a scalable LLM-based method for verifiable assessment of multi-turn tool-calling agents using proxy states inferred from interaction traces.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That LLM state trackers and judges, when given carefully specified scenarios, can infer accurate proxy states and verify goal completion with near-zero hallucination rates and high reliability.","pith_extraction_headline":"Proxy state-based evaluation replaces costly deterministic backends with LLM trackers and judges for benchmarking multi-turn tool-calling agents."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0797ce130752c9cd8aeb36108b5c782c9e8a57972f90fd47d2f697c1296e5f75"},"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":"2602.16246","created_at":"2026-05-18T02:44:31.143458+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.16246v3","created_at":"2026-05-18T02:44:31.143458+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.16246","created_at":"2026-05-18T02:44:31.143458+00:00"},{"alias_kind":"pith_short_12","alias_value":"IGPFAYCXFTYJ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"IGPFAYCXFTYJWAYO","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"IGPFAYCX","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IGPFAYCXFTYJWAYOSLHXOQ4TAP","json":"https://pith.science/pith/IGPFAYCXFTYJWAYOSLHXOQ4TAP.json","graph_json":"https://pith.science/api/pith-number/IGPFAYCXFTYJWAYOSLHXOQ4TAP/graph.json","events_json":"https://pith.science/api/pith-number/IGPFAYCXFTYJWAYOSLHXOQ4TAP/events.json","paper":"https://pith.science/paper/IGPFAYCX"},"agent_actions":{"view_html":"https://pith.science/pith/IGPFAYCXFTYJWAYOSLHXOQ4TAP","download_json":"https://pith.science/pith/IGPFAYCXFTYJWAYOSLHXOQ4TAP.json","view_paper":"https://pith.science/paper/IGPFAYCX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.16246&json=true","fetch_graph":"https://pith.science/api/pith-number/IGPFAYCXFTYJWAYOSLHXOQ4TAP/graph.json","fetch_events":"https://pith.science/api/pith-number/IGPFAYCXFTYJWAYOSLHXOQ4TAP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IGPFAYCXFTYJWAYOSLHXOQ4TAP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IGPFAYCXFTYJWAYOSLHXOQ4TAP/action/storage_attestation","attest_author":"https://pith.science/pith/IGPFAYCXFTYJWAYOSLHXOQ4TAP/action/author_attestation","sign_citation":"https://pith.science/pith/IGPFAYCXFTYJWAYOSLHXOQ4TAP/action/citation_signature","submit_replication":"https://pith.science/pith/IGPFAYCXFTYJWAYOSLHXOQ4TAP/action/replication_record"}},"created_at":"2026-05-18T02:44:31.143458+00:00","updated_at":"2026-05-18T02:44:31.143458+00:00"}