{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DOLAY27BXULHHGYEZF26HAIJNG","short_pith_number":"pith:DOLAY27B","schema_version":"1.0","canonical_sha256":"1b960c6be1bd16739b04c975e38109699b367278f7bae885420e1f3071307736","source":{"kind":"arxiv","id":"2411.06559","version":2},"attestation_state":"computed","paper":{"title":"Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Boyuan Zheng, Boyu Gou, Cheng Chang, Huan Sun, Kai Zhang, Peng Qi, Sanjari Srivastava, Tianci Xue, Yanan Xie, Yu Gu, Yu Su, Yuting Ning","submitted_at":"2024-11-10T18:50:51Z","abstract_excerpt":"Language agents based on large language models (LLMs) have demonstrated great promise in automating web-based tasks. Recent work has shown that incorporating advanced planning algorithms, e.g., tree search, is advantageous over reactive planning for web agents. However, unlike simulated sandbox environments, real-world environments such as the web are rife with irreversible actions. This undermines the feasibility of backtracking, a cornerstone of (tree) search. Overly relying on test-time search also hurts efficiency. We advocate model-based planning for web agents that employs a world model "},"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":"2411.06559","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-10T18:50:51Z","cross_cats_sorted":[],"title_canon_sha256":"398865af1e26353b582b4c8f05de01bf0dd2a927e202cfdde850bdd860ba02f2","abstract_canon_sha256":"eb3a336988e17ef189e812397739a7ded46090bc2c7d306b65e1b4d622b28806"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:13.604633Z","signature_b64":"6DDlyrA2WGy0o4XalunM/vDiyqiVMDEtgVdcscAr1ED0n/V+gSABTmlXv6AceO8JJSlQUUB2mz+jJaEoV+JYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b960c6be1bd16739b04c975e38109699b367278f7bae885420e1f3071307736","last_reissued_at":"2026-07-05T10:42:13.604050Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:13.604050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Boyuan Zheng, Boyu Gou, Cheng Chang, Huan Sun, Kai Zhang, Peng Qi, Sanjari Srivastava, Tianci Xue, Yanan Xie, Yu Gu, Yu Su, Yuting Ning","submitted_at":"2024-11-10T18:50:51Z","abstract_excerpt":"Language agents based on large language models (LLMs) have demonstrated great promise in automating web-based tasks. Recent work has shown that incorporating advanced planning algorithms, e.g., tree search, is advantageous over reactive planning for web agents. However, unlike simulated sandbox environments, real-world environments such as the web are rife with irreversible actions. This undermines the feasibility of backtracking, a cornerstone of (tree) search. Overly relying on test-time search also hurts efficiency. We advocate model-based planning for web agents that employs a world model "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06559","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/2411.06559/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":"2411.06559","created_at":"2026-07-05T10:42:13.604110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.06559v2","created_at":"2026-07-05T10:42:13.604110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06559","created_at":"2026-07-05T10:42:13.604110+00:00"},{"alias_kind":"pith_short_12","alias_value":"DOLAY27BXULH","created_at":"2026-07-05T10:42:13.604110+00:00"},{"alias_kind":"pith_short_16","alias_value":"DOLAY27BXULHHGYE","created_at":"2026-07-05T10:42:13.604110+00:00"},{"alias_kind":"pith_short_8","alias_value":"DOLAY27B","created_at":"2026-07-05T10:42:13.604110+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24597","citing_title":"Qwen-AgentWorld: Language World Models for General Agents","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27330","citing_title":"Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05925","citing_title":"Towards World Models in Biomedical Research","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02031","citing_title":"OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31365","citing_title":"Learning to Adapt: Self-Improving Web Agent via Cognitive-Aware Exploration","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00133","citing_title":"World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and Applications","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10347","citing_title":"How Mobile World Model Guides GUI Agents?","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2504.01990","citing_title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","ref_index":135,"is_internal_anchor":false},{"citing_arxiv_id":"2507.23773","citing_title":"General Agentic Planning Through Simulative Reasoning with World Models","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2603.03784","citing_title":"Specification-Driven Generation and Evaluation of Discrete-Event World Models via the DEVS Formalism","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19219","citing_title":"SimGym: A Framework for A/B Test Simulation in E-Commerce with Traffic-Grounded VLM Agents","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":293,"is_internal_anchor":false},{"citing_arxiv_id":"2506.17697","citing_title":"Beyond Syntax: Action Semantics Learning for App Agents","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2509.08827","citing_title":"A Survey of Reinforcement Learning for Large Reasoning Models","ref_index":168,"is_internal_anchor":false},{"citing_arxiv_id":"2503.09572","citing_title":"Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2601.22149","citing_title":"DynaWeb: Model-Based Reinforcement Learning of Web Agents","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20857","citing_title":"Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory","ref_index":210,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02674","citing_title":"Do Agent Societies Develop Intellectual Elites? The Hidden Power Laws of Collective Cognition in LLM Multi-Agent Systems","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27955","citing_title":"GUI Agents with Reinforcement Learning: Toward Digital Inhabitants","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10347","citing_title":"How Mobile World Model Guides GUI Agents?","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10866","citing_title":"OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16592","citing_title":"Human Cognition in Machines: A Unified Perspective of World Models","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DOLAY27BXULHHGYEZF26HAIJNG","json":"https://pith.science/pith/DOLAY27BXULHHGYEZF26HAIJNG.json","graph_json":"https://pith.science/api/pith-number/DOLAY27BXULHHGYEZF26HAIJNG/graph.json","events_json":"https://pith.science/api/pith-number/DOLAY27BXULHHGYEZF26HAIJNG/events.json","paper":"https://pith.science/paper/DOLAY27B"},"agent_actions":{"view_html":"https://pith.science/pith/DOLAY27BXULHHGYEZF26HAIJNG","download_json":"https://pith.science/pith/DOLAY27BXULHHGYEZF26HAIJNG.json","view_paper":"https://pith.science/paper/DOLAY27B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.06559&json=true","fetch_graph":"https://pith.science/api/pith-number/DOLAY27BXULHHGYEZF26HAIJNG/graph.json","fetch_events":"https://pith.science/api/pith-number/DOLAY27BXULHHGYEZF26HAIJNG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DOLAY27BXULHHGYEZF26HAIJNG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DOLAY27BXULHHGYEZF26HAIJNG/action/storage_attestation","attest_author":"https://pith.science/pith/DOLAY27BXULHHGYEZF26HAIJNG/action/author_attestation","sign_citation":"https://pith.science/pith/DOLAY27BXULHHGYEZF26HAIJNG/action/citation_signature","submit_replication":"https://pith.science/pith/DOLAY27BXULHHGYEZF26HAIJNG/action/replication_record"}},"created_at":"2026-07-05T10:42:13.604110+00:00","updated_at":"2026-07-05T10:42:13.604110+00:00"}