{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2L4FAKGGEOR2HTPLICLDDAS6WF","short_pith_number":"pith:2L4FAKGG","schema_version":"1.0","canonical_sha256":"d2f85028c623a3a3cdeb409631825eb1571db53863612425ae10a455f16d4184","source":{"kind":"arxiv","id":"2408.07199","version":1},"attestation_state":"computed","paper":{"title":"Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Chelsea Finn, Divyansh Garg, Edmund Mills, Naman Garg, Pranav Putta, Rafael Rafailov, Sumeet Motwani","submitted_at":"2024-08-13T20:52:13Z","abstract_excerpt":"Large Language Models (LLMs) have shown remarkable capabilities in natural language tasks requiring complex reasoning, yet their application in agentic, multi-step reasoning within interactive environments remains a difficult challenge. Traditional supervised pre-training on static datasets falls short in enabling autonomous agent capabilities needed to perform complex decision-making in dynamic settings like web navigation. Previous attempts to bridge this ga-through supervised fine-tuning on curated expert demonstrations-often suffer from compounding errors and limited exploration data, resu"},"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":"2408.07199","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-13T20:52:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"aff3059869cd36b4e19efb4f131b57952fd244b5ba2881d3e756d11de12b1848","abstract_canon_sha256":"5b2e27ddc7ea6a265d790907172ae82d31964b8e26bd29d1326fcf4c253266bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T09:35:08.614305Z","signature_b64":"gYVYnw6fQVTn1Ss3jPjd+kwyWiz1HS80d34jADhC0Te37ANAYv0ujBYGCDcLBS/E7d6XIUeSVm9QumNFQ91LAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2f85028c623a3a3cdeb409631825eb1571db53863612425ae10a455f16d4184","last_reissued_at":"2026-05-20T09:35:08.612677Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T09:35:08.612677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Chelsea Finn, Divyansh Garg, Edmund Mills, Naman Garg, Pranav Putta, Rafael Rafailov, Sumeet Motwani","submitted_at":"2024-08-13T20:52:13Z","abstract_excerpt":"Large Language Models (LLMs) have shown remarkable capabilities in natural language tasks requiring complex reasoning, yet their application in agentic, multi-step reasoning within interactive environments remains a difficult challenge. Traditional supervised pre-training on static datasets falls short in enabling autonomous agent capabilities needed to perform complex decision-making in dynamic settings like web navigation. Previous attempts to bridge this ga-through supervised fine-tuning on curated expert demonstrations-often suffer from compounding errors and limited exploration data, resu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07199","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/2408.07199/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":"2408.07199","created_at":"2026-05-20T09:35:08.612736+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.07199v1","created_at":"2026-05-20T09:35:08.612736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07199","created_at":"2026-05-20T09:35:08.612736+00:00"},{"alias_kind":"pith_short_12","alias_value":"2L4FAKGGEOR2","created_at":"2026-05-20T09:35:08.612736+00:00"},{"alias_kind":"pith_short_16","alias_value":"2L4FAKGGEOR2HTPL","created_at":"2026-05-20T09:35:08.612736+00:00"},{"alias_kind":"pith_short_8","alias_value":"2L4FAKGG","created_at":"2026-05-20T09:35:08.612736+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":23,"sample":[{"citing_arxiv_id":"2605.18073","citing_title":"A-ProS: Towards Reliable Autonomous Programming Through Multi-Model Feedback","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20061","citing_title":"Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2506.03610","citing_title":"Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":292,"is_internal_anchor":true},{"citing_arxiv_id":"2506.20332","citing_title":"Mobile-R1: Towards Interactive Capability for VLM-Based Mobile Agent via Systematic Training","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2601.12538","citing_title":"Agentic Reasoning for Large Language Models","ref_index":113,"is_internal_anchor":true},{"citing_arxiv_id":"2601.22149","citing_title":"DynaWeb: Model-Based Reinforcement Learning of Web Agents","ref_index":22,"is_internal_anchor":true},{"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":72,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11853","citing_title":"GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2603.26041","citing_title":"Rethinking Token Pruning for Historical Screenshots in GUI Visual Agents: Semantic, Spatial, and Temporal Perspectives","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2507.21046","citing_title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","ref_index":236,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06130","citing_title":"Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11853","citing_title":"GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27955","citing_title":"GUI Agents with Reinforcement Learning: Toward Digital Inhabitants","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09497","citing_title":"Don't Click That: Teaching Web Agents to Resist Deceptive Interfaces","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06642","citing_title":"StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06130","citing_title":"Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22577","citing_title":"QuantClaw: Precision Where It Matters for OpenClaw","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2505.10978","citing_title":"Group-in-Group Policy Optimization for LLM Agent Training","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07774","citing_title":"RoboAgent: Chaining Basic Capabilities for Embodied Task Planning","ref_index":72,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06130","citing_title":"Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14877","citing_title":"Does RL Expand the Capability Boundary of LLM Agents? A PASS@(k,T) Analysis","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15972","citing_title":"Weak-Link Optimization for Multi-Agent Reasoning and Collaboration","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2L4FAKGGEOR2HTPLICLDDAS6WF","json":"https://pith.science/pith/2L4FAKGGEOR2HTPLICLDDAS6WF.json","graph_json":"https://pith.science/api/pith-number/2L4FAKGGEOR2HTPLICLDDAS6WF/graph.json","events_json":"https://pith.science/api/pith-number/2L4FAKGGEOR2HTPLICLDDAS6WF/events.json","paper":"https://pith.science/paper/2L4FAKGG"},"agent_actions":{"view_html":"https://pith.science/pith/2L4FAKGGEOR2HTPLICLDDAS6WF","download_json":"https://pith.science/pith/2L4FAKGGEOR2HTPLICLDDAS6WF.json","view_paper":"https://pith.science/paper/2L4FAKGG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.07199&json=true","fetch_graph":"https://pith.science/api/pith-number/2L4FAKGGEOR2HTPLICLDDAS6WF/graph.json","fetch_events":"https://pith.science/api/pith-number/2L4FAKGGEOR2HTPLICLDDAS6WF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2L4FAKGGEOR2HTPLICLDDAS6WF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2L4FAKGGEOR2HTPLICLDDAS6WF/action/storage_attestation","attest_author":"https://pith.science/pith/2L4FAKGGEOR2HTPLICLDDAS6WF/action/author_attestation","sign_citation":"https://pith.science/pith/2L4FAKGGEOR2HTPLICLDDAS6WF/action/citation_signature","submit_replication":"https://pith.science/pith/2L4FAKGGEOR2HTPLICLDDAS6WF/action/replication_record"}},"created_at":"2026-05-20T09:35:08.612736+00:00","updated_at":"2026-05-20T09:35:08.612736+00:00"}