{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O6UXE24BNJDXBSB5Y4BRRT5CKR","short_pith_number":"pith:O6UXE24B","schema_version":"1.0","canonical_sha256":"77a9726b816a4770c83dc70318cfa2544b577c947dbb540df91294ab499bd3ec","source":{"kind":"arxiv","id":"2410.10934","version":2},"attestation_state":"computed","paper":{"title":"Agent-as-a-Judge: Evaluate Agents with Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Changsheng Zhao, Dmitrii Khizbullin, Dylan Ashley, Ernie Chang, J\\\"urgen Schmidhuber, Mingchen Zhuge, Raghuraman Krishnamoorthi, Vikas Chandra, Wenyi Wang, Yangyang Shi, Yuandong Tian, Yunyang Xiong, Zechun Liu","submitted_at":"2024-10-14T17:57:02Z","abstract_excerpt":"Contemporary evaluation techniques are inadequate for agentic systems. These approaches either focus exclusively on final outcomes -- ignoring the step-by-step nature of agentic systems, or require excessive manual labour. To address this, we introduce the Agent-as-a-Judge framework, wherein agentic systems are used to evaluate agentic systems. This is an organic extension of the LLM-as-a-Judge framework, incorporating agentic features that enable intermediate feedback for the entire task-solving process. We apply the Agent-as-a-Judge to the task of code generation. To overcome issues with exi"},"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":"2410.10934","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-14T17:57:02Z","cross_cats_sorted":[],"title_canon_sha256":"a8e8751641f103e15e27ac2210a50eb37624d02e2216c3ee6d047288023a2b22","abstract_canon_sha256":"520597991c36704db0d57674d2c308195516721671833edb38b32e51a726d6fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:50.071437Z","signature_b64":"5VbnIvhVfmQmML37KMSQbZZx4XPYaTHpzYoJh4pDyvJxgMqLV0P+bPp5g0HUuyngKhHr7A04+6HVPovKtNq7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77a9726b816a4770c83dc70318cfa2544b577c947dbb540df91294ab499bd3ec","last_reissued_at":"2026-07-05T09:21:50.070955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:50.070955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Agent-as-a-Judge: Evaluate Agents with Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Changsheng Zhao, Dmitrii Khizbullin, Dylan Ashley, Ernie Chang, J\\\"urgen Schmidhuber, Mingchen Zhuge, Raghuraman Krishnamoorthi, Vikas Chandra, Wenyi Wang, Yangyang Shi, Yuandong Tian, Yunyang Xiong, Zechun Liu","submitted_at":"2024-10-14T17:57:02Z","abstract_excerpt":"Contemporary evaluation techniques are inadequate for agentic systems. These approaches either focus exclusively on final outcomes -- ignoring the step-by-step nature of agentic systems, or require excessive manual labour. To address this, we introduce the Agent-as-a-Judge framework, wherein agentic systems are used to evaluate agentic systems. This is an organic extension of the LLM-as-a-Judge framework, incorporating agentic features that enable intermediate feedback for the entire task-solving process. We apply the Agent-as-a-Judge to the task of code generation. To overcome issues with exi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10934","kind":"arxiv","version":2},"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/2410.10934/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":"2410.10934","created_at":"2026-07-05T09:21:50.071012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10934v2","created_at":"2026-07-05T09:21:50.071012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10934","created_at":"2026-07-05T09:21:50.071012+00:00"},{"alias_kind":"pith_short_12","alias_value":"O6UXE24BNJDX","created_at":"2026-07-05T09:21:50.071012+00:00"},{"alias_kind":"pith_short_16","alias_value":"O6UXE24BNJDXBSB5","created_at":"2026-07-05T09:21:50.071012+00:00"},{"alias_kind":"pith_short_8","alias_value":"O6UXE24B","created_at":"2026-07-05T09:21:50.071012+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":32,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.07946","citing_title":"DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Tasks","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2607.06157","citing_title":"LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability","ref_index":123,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24834","citing_title":"Accuracy and Satisfaction in Multi-Turn LLM Dialogues for NFR Assessment","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24004","citing_title":"Towards Spec Learning: Inference-Time Alignment from Preference Pairs","ref_index":133,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21654","citing_title":"ChainWorld: Composing Long-Horizon Desktop Workloads from Atomic OSWorld Tasks","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21627","citing_title":"Counsel: A Meta-Evaluation Dataset for Agentic Tasks","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20950","citing_title":"Power Systems Agent Benchmark: Executable Evaluation of AI Agents in Electric Power Engineering","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20950","citing_title":"Power Systems Agent Benchmark: Executable Evaluation of AI Agents in Electric Power Engineering","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01874","citing_title":"SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11176","citing_title":"Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03467","citing_title":"StepFinder: A Temporal Semantic Framework for Failure Attribution in Multi-Agent Systems","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20530","citing_title":"AgentAtlas: Beyond Outcome Leaderboards for LLM Agents","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24004","citing_title":"Towards Spec Learning: Inference-Time Alignment from Preference Pairs","ref_index":133,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30246","citing_title":"Clarus: Coordinating Autonomous Research Agents toward Web-Scale Scientific Collaboration","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29727","citing_title":"DeepTrans Studio: Turning Expert Interventions into Shared Team Knowledge in Agentic Translation Workflows","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2411.15594","citing_title":"A Survey on LLM-as-a-Judge","ref_index":233,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20530","citing_title":"AgentAtlas: Beyond Outcome Leaderboards for LLM Agents","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19932","citing_title":"PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2509.14528","citing_title":"Why Johnny Can't Use Agents: Industry Aspirations vs. User Realities with AI Agents","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2510.02837","citing_title":"Beyond the Final Answer: Evaluating the Reasoning Trajectories of Tool-Augmented Agents","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2510.23883","citing_title":"Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges","ref_index":245,"is_internal_anchor":false},{"citing_arxiv_id":"2601.15808","citing_title":"Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2508.07407","citing_title":"A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems","ref_index":125,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08715","citing_title":"AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O6UXE24BNJDXBSB5Y4BRRT5CKR","json":"https://pith.science/pith/O6UXE24BNJDXBSB5Y4BRRT5CKR.json","graph_json":"https://pith.science/api/pith-number/O6UXE24BNJDXBSB5Y4BRRT5CKR/graph.json","events_json":"https://pith.science/api/pith-number/O6UXE24BNJDXBSB5Y4BRRT5CKR/events.json","paper":"https://pith.science/paper/O6UXE24B"},"agent_actions":{"view_html":"https://pith.science/pith/O6UXE24BNJDXBSB5Y4BRRT5CKR","download_json":"https://pith.science/pith/O6UXE24BNJDXBSB5Y4BRRT5CKR.json","view_paper":"https://pith.science/paper/O6UXE24B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10934&json=true","fetch_graph":"https://pith.science/api/pith-number/O6UXE24BNJDXBSB5Y4BRRT5CKR/graph.json","fetch_events":"https://pith.science/api/pith-number/O6UXE24BNJDXBSB5Y4BRRT5CKR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O6UXE24BNJDXBSB5Y4BRRT5CKR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O6UXE24BNJDXBSB5Y4BRRT5CKR/action/storage_attestation","attest_author":"https://pith.science/pith/O6UXE24BNJDXBSB5Y4BRRT5CKR/action/author_attestation","sign_citation":"https://pith.science/pith/O6UXE24BNJDXBSB5Y4BRRT5CKR/action/citation_signature","submit_replication":"https://pith.science/pith/O6UXE24BNJDXBSB5Y4BRRT5CKR/action/replication_record"}},"created_at":"2026-07-05T09:21:50.071012+00:00","updated_at":"2026-07-05T09:21:50.071012+00:00"}