{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QW4WJZYUXSHJWI54E5HWU2OITF","short_pith_number":"pith:QW4WJZYU","schema_version":"1.0","canonical_sha256":"85b964e714bc8e9b23bc274f6a69c899649bdeac146e4d040d68b684290341eb","source":{"kind":"arxiv","id":"2412.04759","version":2},"attestation_state":"computed","paper":{"title":"REGENT: A Retrieval-Augmented Generalist Agent That Can Act In-Context in New Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dinesh Jayaraman, Insup Lee, Kaustubh Sridhar, Souradeep Dutta","submitted_at":"2024-12-06T03:54:55Z","abstract_excerpt":"Building generalist agents that can rapidly adapt to new environments is a key challenge for deploying AI in the digital and real worlds. Is scaling current agent architectures the most effective way to build generalist agents? We propose a novel approach to pre-train relatively small policies on relatively small datasets and adapt them to unseen environments via in-context learning, without any finetuning. Our key idea is that retrieval offers a powerful bias for fast adaptation. Indeed, we demonstrate that even a simple retrieval-based 1-nearest neighbor agent offers a surprisingly strong ba"},"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":"2412.04759","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-06T03:54:55Z","cross_cats_sorted":[],"title_canon_sha256":"dce12e9dbe2edbac1fe18ec90aac85b8a5e2d3774d570671bee0876976f99ac5","abstract_canon_sha256":"911d74c9f9e594d3abac4ca5b0f81103134f8e84ba2ab0671022a1866c8f9107"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:46.179858Z","signature_b64":"zuSo32lUJuvA3ssS4+gx78nV/RKM6PbWlkeUvTUtNC/2WIp8Mj0KC9bNdT+3awxhhd5N9+uj9aqEHcVuSAvXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85b964e714bc8e9b23bc274f6a69c899649bdeac146e4d040d68b684290341eb","last_reissued_at":"2026-07-05T10:18:46.179335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:46.179335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"REGENT: A Retrieval-Augmented Generalist Agent That Can Act In-Context in New Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dinesh Jayaraman, Insup Lee, Kaustubh Sridhar, Souradeep Dutta","submitted_at":"2024-12-06T03:54:55Z","abstract_excerpt":"Building generalist agents that can rapidly adapt to new environments is a key challenge for deploying AI in the digital and real worlds. Is scaling current agent architectures the most effective way to build generalist agents? We propose a novel approach to pre-train relatively small policies on relatively small datasets and adapt them to unseen environments via in-context learning, without any finetuning. Our key idea is that retrieval offers a powerful bias for fast adaptation. Indeed, we demonstrate that even a simple retrieval-based 1-nearest neighbor agent offers a surprisingly strong ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04759","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/2412.04759/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":"2412.04759","created_at":"2026-07-05T10:18:46.179397+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04759v2","created_at":"2026-07-05T10:18:46.179397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04759","created_at":"2026-07-05T10:18:46.179397+00:00"},{"alias_kind":"pith_short_12","alias_value":"QW4WJZYUXSHJ","created_at":"2026-07-05T10:18:46.179397+00:00"},{"alias_kind":"pith_short_16","alias_value":"QW4WJZYUXSHJWI54","created_at":"2026-07-05T10:18:46.179397+00:00"},{"alias_kind":"pith_short_8","alias_value":"QW4WJZYU","created_at":"2026-07-05T10:18:46.179397+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24962","citing_title":"Towards Scalable Multi-Task Reinforcement Learning with Large Decision Models","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QW4WJZYUXSHJWI54E5HWU2OITF","json":"https://pith.science/pith/QW4WJZYUXSHJWI54E5HWU2OITF.json","graph_json":"https://pith.science/api/pith-number/QW4WJZYUXSHJWI54E5HWU2OITF/graph.json","events_json":"https://pith.science/api/pith-number/QW4WJZYUXSHJWI54E5HWU2OITF/events.json","paper":"https://pith.science/paper/QW4WJZYU"},"agent_actions":{"view_html":"https://pith.science/pith/QW4WJZYUXSHJWI54E5HWU2OITF","download_json":"https://pith.science/pith/QW4WJZYUXSHJWI54E5HWU2OITF.json","view_paper":"https://pith.science/paper/QW4WJZYU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04759&json=true","fetch_graph":"https://pith.science/api/pith-number/QW4WJZYUXSHJWI54E5HWU2OITF/graph.json","fetch_events":"https://pith.science/api/pith-number/QW4WJZYUXSHJWI54E5HWU2OITF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QW4WJZYUXSHJWI54E5HWU2OITF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QW4WJZYUXSHJWI54E5HWU2OITF/action/storage_attestation","attest_author":"https://pith.science/pith/QW4WJZYUXSHJWI54E5HWU2OITF/action/author_attestation","sign_citation":"https://pith.science/pith/QW4WJZYUXSHJWI54E5HWU2OITF/action/citation_signature","submit_replication":"https://pith.science/pith/QW4WJZYUXSHJWI54E5HWU2OITF/action/replication_record"}},"created_at":"2026-07-05T10:18:46.179397+00:00","updated_at":"2026-07-05T10:18:46.179397+00:00"}