{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZBMBCTKTJMMB4TF6JPU6KTOOF4","short_pith_number":"pith:ZBMBCTKT","schema_version":"1.0","canonical_sha256":"c858114d534b181e4cbe4be9e54dce2f0964ff7fdee4a3f0d0f868f1c8bb4607","source":{"kind":"arxiv","id":"2410.13232","version":2},"attestation_state":"computed","paper":{"title":"Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongha Lee, Gwanwoo Song, Hyungjoo Chae, Jihoon Kim, Jinyoung Yeo, Kai Tzu-iunn Ong, Minju Gwak, Namyoung Kim, Sunghwan Kim","submitted_at":"2024-10-17T05:37:00Z","abstract_excerpt":"Large language models (LLMs) have recently gained much attention in building autonomous agents. However, the performance of current LLM-based web agents in long-horizon tasks is far from optimal, often yielding errors such as repeatedly buying a non-refundable flight ticket. By contrast, humans can avoid such an irreversible mistake, as we have an awareness of the potential outcomes (e.g., losing money) of our actions, also known as the \"world model\". Motivated by this, our study first starts with preliminary analyses, confirming the absence of world models in current LLMs (e.g., GPT-4o, Claud"},"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":"2410.13232","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-17T05:37:00Z","cross_cats_sorted":[],"title_canon_sha256":"1a68e7b120850c813a1c72ed5384f1f3bce752206190844ad2cb2727ca6faf5c","abstract_canon_sha256":"b3c3b81a90f57ea86c8395c1a0b242361d1228ccf9a49e710233e8811cdce8a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:16.112820Z","signature_b64":"vvjJRRC2SNucnY3ZQYfzJ6A9tY3gyvyk56IyR44iCDfURpR202jfqWcEuffD1I+4z7eMvQ8+81AIXaz3G6N+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c858114d534b181e4cbe4be9e54dce2f0964ff7fdee4a3f0d0f868f1c8bb4607","last_reissued_at":"2026-07-05T10:41:16.112355Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:16.112355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongha Lee, Gwanwoo Song, Hyungjoo Chae, Jihoon Kim, Jinyoung Yeo, Kai Tzu-iunn Ong, Minju Gwak, Namyoung Kim, Sunghwan Kim","submitted_at":"2024-10-17T05:37:00Z","abstract_excerpt":"Large language models (LLMs) have recently gained much attention in building autonomous agents. However, the performance of current LLM-based web agents in long-horizon tasks is far from optimal, often yielding errors such as repeatedly buying a non-refundable flight ticket. By contrast, humans can avoid such an irreversible mistake, as we have an awareness of the potential outcomes (e.g., losing money) of our actions, also known as the \"world model\". Motivated by this, our study first starts with preliminary analyses, confirming the absence of world models in current LLMs (e.g., GPT-4o, Claud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13232","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/2410.13232/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":"2410.13232","created_at":"2026-07-05T10:41:16.112412+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13232v2","created_at":"2026-07-05T10:41:16.112412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13232","created_at":"2026-07-05T10:41:16.112412+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZBMBCTKTJMMB","created_at":"2026-07-05T10:41:16.112412+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZBMBCTKTJMMB4TF6","created_at":"2026-07-05T10:41:16.112412+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZBMBCTKT","created_at":"2026-07-05T10:41:16.112412+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17929","citing_title":"PreAct: Computer-Using Agents that Get Faster on Repeated Tasks","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10347","citing_title":"How Mobile World Model Guides GUI Agents?","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2501.16150","citing_title":"A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2507.23773","citing_title":"General Agentic Planning Through Simulative Reasoning with World Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":275,"is_internal_anchor":false},{"citing_arxiv_id":"2506.17697","citing_title":"Beyond Syntax: Action Semantics Learning for App Agents","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2503.09572","citing_title":"Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2506.15841","citing_title":"MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2603.26041","citing_title":"Rethinking Token Pruning for Historical Screenshots in GUI Visual Agents: Semantic, Spatial, and Temporal Perspectives","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10347","citing_title":"How Mobile World Model Guides GUI Agents?","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18133","citing_title":"Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futures","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16007","citing_title":"MemExplorer: Navigating the Heterogeneous Memory Design Space for Agentic Inference NPUs","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZBMBCTKTJMMB4TF6JPU6KTOOF4","json":"https://pith.science/pith/ZBMBCTKTJMMB4TF6JPU6KTOOF4.json","graph_json":"https://pith.science/api/pith-number/ZBMBCTKTJMMB4TF6JPU6KTOOF4/graph.json","events_json":"https://pith.science/api/pith-number/ZBMBCTKTJMMB4TF6JPU6KTOOF4/events.json","paper":"https://pith.science/paper/ZBMBCTKT"},"agent_actions":{"view_html":"https://pith.science/pith/ZBMBCTKTJMMB4TF6JPU6KTOOF4","download_json":"https://pith.science/pith/ZBMBCTKTJMMB4TF6JPU6KTOOF4.json","view_paper":"https://pith.science/paper/ZBMBCTKT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13232&json=true","fetch_graph":"https://pith.science/api/pith-number/ZBMBCTKTJMMB4TF6JPU6KTOOF4/graph.json","fetch_events":"https://pith.science/api/pith-number/ZBMBCTKTJMMB4TF6JPU6KTOOF4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZBMBCTKTJMMB4TF6JPU6KTOOF4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZBMBCTKTJMMB4TF6JPU6KTOOF4/action/storage_attestation","attest_author":"https://pith.science/pith/ZBMBCTKTJMMB4TF6JPU6KTOOF4/action/author_attestation","sign_citation":"https://pith.science/pith/ZBMBCTKTJMMB4TF6JPU6KTOOF4/action/citation_signature","submit_replication":"https://pith.science/pith/ZBMBCTKTJMMB4TF6JPU6KTOOF4/action/replication_record"}},"created_at":"2026-07-05T10:41:16.112412+00:00","updated_at":"2026-07-05T10:41:16.112412+00:00"}