{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BRBLUY7IL3VNLIIXKISHUN7GZI","short_pith_number":"pith:BRBLUY7I","schema_version":"1.0","canonical_sha256":"0c42ba63e85eead5a11752247a37e6ca2ce692dff2ff5dfa46a667f92fce95a8","source":{"kind":"arxiv","id":"2505.22942","version":2},"attestation_state":"computed","paper":{"title":"WorkForceAgent-R1: Incentivizing Reasoning Capability in LLM-based Web Agents via Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chao Zhang, Di Jin, Hanrui Wang, Jiaao Chen, Wenqi Shi, Yuchen Zhuang","submitted_at":"2025-05-28T23:45:28Z","abstract_excerpt":"Large language models (LLMs)-empowered web agents enables automating complex, real-time web navigation tasks in enterprise environments. However, existing web agents relying on supervised fine-tuning (SFT) often struggle with generalization and robustness due to insufficient reasoning capabilities when handling the inherently dynamic nature of web interactions. In this study, we introduce WorkForceAgent-R1, an LLM-based web agent trained using a rule-based R1-style reinforcement learning framework designed explicitly to enhance single-step reasoning and planning for business-oriented web navig"},"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":"2505.22942","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T23:45:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"49f55cc32983acb67b95e91024f56c7c3ff91d4f503df68cf56c5130121ec866","abstract_canon_sha256":"a1ee2cafc8efe52e624f2174f298adee12f4acbbfbb2a17a2c8b912d3de156b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:46.293854Z","signature_b64":"j3xg2rueZQndUgpAlParyoDztB+IUXDMVxW38fUZafRyL2+TclxkE/hkH3w2ebS6IUQsyZoeRMcx8+Tsf+N/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c42ba63e85eead5a11752247a37e6ca2ce692dff2ff5dfa46a667f92fce95a8","last_reissued_at":"2026-07-05T11:17:46.293270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:46.293270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WorkForceAgent-R1: Incentivizing Reasoning Capability in LLM-based Web Agents via Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chao Zhang, Di Jin, Hanrui Wang, Jiaao Chen, Wenqi Shi, Yuchen Zhuang","submitted_at":"2025-05-28T23:45:28Z","abstract_excerpt":"Large language models (LLMs)-empowered web agents enables automating complex, real-time web navigation tasks in enterprise environments. However, existing web agents relying on supervised fine-tuning (SFT) often struggle with generalization and robustness due to insufficient reasoning capabilities when handling the inherently dynamic nature of web interactions. In this study, we introduce WorkForceAgent-R1, an LLM-based web agent trained using a rule-based R1-style reinforcement learning framework designed explicitly to enhance single-step reasoning and planning for business-oriented web navig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22942","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/2505.22942/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":"2505.22942","created_at":"2026-07-05T11:17:46.293340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22942v2","created_at":"2026-07-05T11:17:46.293340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22942","created_at":"2026-07-05T11:17:46.293340+00:00"},{"alias_kind":"pith_short_12","alias_value":"BRBLUY7IL3VN","created_at":"2026-07-05T11:17:46.293340+00:00"},{"alias_kind":"pith_short_16","alias_value":"BRBLUY7IL3VNLIIX","created_at":"2026-07-05T11:17:46.293340+00:00"},{"alias_kind":"pith_short_8","alias_value":"BRBLUY7I","created_at":"2026-07-05T11:17:46.293340+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.22149","citing_title":"DynaWeb: Model-Based Reinforcement Learning of Web Agents","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BRBLUY7IL3VNLIIXKISHUN7GZI","json":"https://pith.science/pith/BRBLUY7IL3VNLIIXKISHUN7GZI.json","graph_json":"https://pith.science/api/pith-number/BRBLUY7IL3VNLIIXKISHUN7GZI/graph.json","events_json":"https://pith.science/api/pith-number/BRBLUY7IL3VNLIIXKISHUN7GZI/events.json","paper":"https://pith.science/paper/BRBLUY7I"},"agent_actions":{"view_html":"https://pith.science/pith/BRBLUY7IL3VNLIIXKISHUN7GZI","download_json":"https://pith.science/pith/BRBLUY7IL3VNLIIXKISHUN7GZI.json","view_paper":"https://pith.science/paper/BRBLUY7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22942&json=true","fetch_graph":"https://pith.science/api/pith-number/BRBLUY7IL3VNLIIXKISHUN7GZI/graph.json","fetch_events":"https://pith.science/api/pith-number/BRBLUY7IL3VNLIIXKISHUN7GZI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BRBLUY7IL3VNLIIXKISHUN7GZI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BRBLUY7IL3VNLIIXKISHUN7GZI/action/storage_attestation","attest_author":"https://pith.science/pith/BRBLUY7IL3VNLIIXKISHUN7GZI/action/author_attestation","sign_citation":"https://pith.science/pith/BRBLUY7IL3VNLIIXKISHUN7GZI/action/citation_signature","submit_replication":"https://pith.science/pith/BRBLUY7IL3VNLIIXKISHUN7GZI/action/replication_record"}},"created_at":"2026-07-05T11:17:46.293340+00:00","updated_at":"2026-07-05T11:17:46.293340+00:00"}