{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XPIFDTADCR4L4ERW43ZNHBNDQD","short_pith_number":"pith:XPIFDTAD","schema_version":"1.0","canonical_sha256":"bbd051cc031478be1236e6f2d385a380cb2835101d0b9c9507f33d6ee6c44d61","source":{"kind":"arxiv","id":"2511.20297","version":2},"attestation_state":"computed","paper":{"title":"Improving Language Agents through BREW: Bootstrapping expeRientially-learned Environmental knoWledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gustavo Soares, Param Biyani, Priyanshu Gupta, Roshni Iyer, Shashank Kirtania, Sumit Gulwani, Yasharth Bajpai","submitted_at":"2025-11-25T13:34:54Z","abstract_excerpt":"Large Language Model (LLM)-based agents are increasingly capable of complex, multi-step tasks such as GUI automation, tool use, and data manipulation, yet they cannot learn from experience: each new session rediscovers solutions from scratch. We introduce BREW (Bootstrapping expeRientially-learned Environmental knoWledge), a framework that distills an agent's past interaction trajectories into a structured, retrievable knowledge base (KB) of natural-language recipes, concept-level procedural documents that capture what to do, when it applies, and what to watch out for.\n  Drawing on the princip"},"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":"2511.20297","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-11-25T13:34:54Z","cross_cats_sorted":[],"title_canon_sha256":"cd13d869b2f54d1f944688ffa0068dced3844344b039a38c13e56c2e3131bafc","abstract_canon_sha256":"e0dda33ae602b2f638ba261cbcef7e8a26554107b2c53ec088391488c9710b39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T01:17:51.001835Z","signature_b64":"r3pUBlftHKbBnR35cGN7PITBuYEhjAm8/NBnquz2MOnLr1j42ELzpp069S91chEIWLKIfgiA+cWghUrU9vhZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbd051cc031478be1236e6f2d385a380cb2835101d0b9c9507f33d6ee6c44d61","last_reissued_at":"2026-07-13T01:17:51.000199Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T01:17:51.000199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Language Agents through BREW: Bootstrapping expeRientially-learned Environmental knoWledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gustavo Soares, Param Biyani, Priyanshu Gupta, Roshni Iyer, Shashank Kirtania, Sumit Gulwani, Yasharth Bajpai","submitted_at":"2025-11-25T13:34:54Z","abstract_excerpt":"Large Language Model (LLM)-based agents are increasingly capable of complex, multi-step tasks such as GUI automation, tool use, and data manipulation, yet they cannot learn from experience: each new session rediscovers solutions from scratch. We introduce BREW (Bootstrapping expeRientially-learned Environmental knoWledge), a framework that distills an agent's past interaction trajectories into a structured, retrievable knowledge base (KB) of natural-language recipes, concept-level procedural documents that capture what to do, when it applies, and what to watch out for.\n  Drawing on the princip"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.20297","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/2511.20297/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":"2511.20297","created_at":"2026-07-13T01:17:51.000986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.20297v2","created_at":"2026-07-13T01:17:51.000986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.20297","created_at":"2026-07-13T01:17:51.000986+00:00"},{"alias_kind":"pith_short_12","alias_value":"XPIFDTADCR4L","created_at":"2026-07-13T01:17:51.000986+00:00"},{"alias_kind":"pith_short_16","alias_value":"XPIFDTADCR4L4ERW","created_at":"2026-07-13T01:17:51.000986+00:00"},{"alias_kind":"pith_short_8","alias_value":"XPIFDTAD","created_at":"2026-07-13T01:17:51.000986+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XPIFDTADCR4L4ERW43ZNHBNDQD","json":"https://pith.science/pith/XPIFDTADCR4L4ERW43ZNHBNDQD.json","graph_json":"https://pith.science/api/pith-number/XPIFDTADCR4L4ERW43ZNHBNDQD/graph.json","events_json":"https://pith.science/api/pith-number/XPIFDTADCR4L4ERW43ZNHBNDQD/events.json","paper":"https://pith.science/paper/XPIFDTAD"},"agent_actions":{"view_html":"https://pith.science/pith/XPIFDTADCR4L4ERW43ZNHBNDQD","download_json":"https://pith.science/pith/XPIFDTADCR4L4ERW43ZNHBNDQD.json","view_paper":"https://pith.science/paper/XPIFDTAD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.20297&json=true","fetch_graph":"https://pith.science/api/pith-number/XPIFDTADCR4L4ERW43ZNHBNDQD/graph.json","fetch_events":"https://pith.science/api/pith-number/XPIFDTADCR4L4ERW43ZNHBNDQD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XPIFDTADCR4L4ERW43ZNHBNDQD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XPIFDTADCR4L4ERW43ZNHBNDQD/action/storage_attestation","attest_author":"https://pith.science/pith/XPIFDTADCR4L4ERW43ZNHBNDQD/action/author_attestation","sign_citation":"https://pith.science/pith/XPIFDTADCR4L4ERW43ZNHBNDQD/action/citation_signature","submit_replication":"https://pith.science/pith/XPIFDTADCR4L4ERW43ZNHBNDQD/action/replication_record"}},"created_at":"2026-07-13T01:17:51.000986+00:00","updated_at":"2026-07-13T01:17:51.000986+00:00"}