{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AKIMIPVLZM6K7QKVMTFCTG2NY7","short_pith_number":"pith:AKIMIPVL","schema_version":"1.0","canonical_sha256":"0290c43eabcb3cafc15564ca299b4dc7fc51ce73d258632fe79a133e84c8ec65","source":{"kind":"arxiv","id":"2511.12997","version":2},"attestation_state":"computed","paper":{"title":"WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Genglin Liu, Hejie Cui, Sarah Zhang, Sha Li, Shijie Geng, Tianyi Liu, Xin Liu","submitted_at":"2025-11-17T05:38:50Z","abstract_excerpt":"Multimodal LLM-powered agents have recently demonstrated impressive capabilities in web navigation, enabling agents to complete complex browsing tasks across diverse domains. However, current agents struggle with repetitive errors and lack the ability to learn from past experiences across sessions, limiting their long-term robustness and sample efficiency. We introduce WebCoach, a model-agnostic self-evolving framework that equips web browsing agents with persistent cross-session memory, enabling improved long-term planning, reflection, and continual learning without retraining. WebCoach consi"},"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":"2511.12997","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-11-17T05:38:50Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b687720d925d7387c20c3fd83f2ef883604f3ed4285f80f57738d5b5bf38282b","abstract_canon_sha256":"ffb972664d5b519b32df43d849115cebbb8fe7232b6e60d947b1b3385d4ff37a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T00:23:05.955088Z","signature_b64":"brP4RQ5f60V8Uy0q11F44FHsX7o2HwGn0m4KYv6m/MCxuxulPZ59ovhRWwKRAuyyT+7fuHSP8d5e8LbH4f5RDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0290c43eabcb3cafc15564ca299b4dc7fc51ce73d258632fe79a133e84c8ec65","last_reissued_at":"2026-07-24T00:23:05.954076Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T00:23:05.954076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Genglin Liu, Hejie Cui, Sarah Zhang, Sha Li, Shijie Geng, Tianyi Liu, Xin Liu","submitted_at":"2025-11-17T05:38:50Z","abstract_excerpt":"Multimodal LLM-powered agents have recently demonstrated impressive capabilities in web navigation, enabling agents to complete complex browsing tasks across diverse domains. However, current agents struggle with repetitive errors and lack the ability to learn from past experiences across sessions, limiting their long-term robustness and sample efficiency. We introduce WebCoach, a model-agnostic self-evolving framework that equips web browsing agents with persistent cross-session memory, enabling improved long-term planning, reflection, and continual learning without retraining. WebCoach consi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.12997","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/2511.12997/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":"2511.12997","created_at":"2026-07-24T00:23:05.954560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.12997v2","created_at":"2026-07-24T00:23:05.954560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.12997","created_at":"2026-07-24T00:23:05.954560+00:00"},{"alias_kind":"pith_short_12","alias_value":"AKIMIPVLZM6K","created_at":"2026-07-24T00:23:05.954560+00:00"},{"alias_kind":"pith_short_16","alias_value":"AKIMIPVLZM6K7QKV","created_at":"2026-07-24T00:23:05.954560+00:00"},{"alias_kind":"pith_short_8","alias_value":"AKIMIPVL","created_at":"2026-07-24T00:23:05.954560+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.23939","citing_title":"DRIVE: Modeling Skills at the Reasoning and Interaction Levels for Web Agents under Continual Learning","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AKIMIPVLZM6K7QKVMTFCTG2NY7","json":"https://pith.science/pith/AKIMIPVLZM6K7QKVMTFCTG2NY7.json","graph_json":"https://pith.science/api/pith-number/AKIMIPVLZM6K7QKVMTFCTG2NY7/graph.json","events_json":"https://pith.science/api/pith-number/AKIMIPVLZM6K7QKVMTFCTG2NY7/events.json","paper":"https://pith.science/paper/AKIMIPVL"},"agent_actions":{"view_html":"https://pith.science/pith/AKIMIPVLZM6K7QKVMTFCTG2NY7","download_json":"https://pith.science/pith/AKIMIPVLZM6K7QKVMTFCTG2NY7.json","view_paper":"https://pith.science/paper/AKIMIPVL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.12997&json=true","fetch_graph":"https://pith.science/api/pith-number/AKIMIPVLZM6K7QKVMTFCTG2NY7/graph.json","fetch_events":"https://pith.science/api/pith-number/AKIMIPVLZM6K7QKVMTFCTG2NY7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AKIMIPVLZM6K7QKVMTFCTG2NY7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AKIMIPVLZM6K7QKVMTFCTG2NY7/action/storage_attestation","attest_author":"https://pith.science/pith/AKIMIPVLZM6K7QKVMTFCTG2NY7/action/author_attestation","sign_citation":"https://pith.science/pith/AKIMIPVLZM6K7QKVMTFCTG2NY7/action/citation_signature","submit_replication":"https://pith.science/pith/AKIMIPVLZM6K7QKVMTFCTG2NY7/action/replication_record"}},"created_at":"2026-07-24T00:23:05.954560+00:00","updated_at":"2026-07-24T00:23:05.954560+00:00"}