{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WC2YVJNSA7IF42VOUWDSSF42GJ","short_pith_number":"pith:WC2YVJNS","schema_version":"1.0","canonical_sha256":"b0b58aa5b207d05e6aaea58729179a32772e9b92002eb4a198502ab2e98b2c1b","source":{"kind":"arxiv","id":"2406.08747","version":2},"attestation_state":"computed","paper":{"title":"StreamBench: Towards Benchmarking Continuous Improvement of Language Agents","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheng-Kuang Wu, Chieh-Yen Lin, Hung-yi Lee, Yun-Nung Chen, Zhi Rui Tam","submitted_at":"2024-06-13T02:08:28Z","abstract_excerpt":"Recent works have shown that large language model (LLM) agents are able to improve themselves from experience, which is an important ability for continuous enhancement post-deployment. However, existing benchmarks primarily evaluate their innate capabilities and do not assess their ability to improve over time. To address this gap, we introduce StreamBench, a pioneering benchmark designed to evaluate the continuous improvement of LLM agents over an input-feedback sequence. StreamBench simulates an online learning environment where LLMs receive a continuous flow of feedback stream and iterative"},"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":"2406.08747","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T02:08:28Z","cross_cats_sorted":[],"title_canon_sha256":"ba86c64a394c5a8a602e4bbf94b3f0ef59ee833003138f9713f58f08331a7eca","abstract_canon_sha256":"8dc305769581aba0680a688c583317df7dd94f51b75d659c5f9c7cb36bf6b9b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:51.260474Z","signature_b64":"XBkinI4ygBqkAijUqmLN0PVcCL25yU505/E7althDjkHNR8rtwpqR1ytnypBsGkml76AcNLkFvU+yCqeGJ4TAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0b58aa5b207d05e6aaea58729179a32772e9b92002eb4a198502ab2e98b2c1b","last_reissued_at":"2026-07-05T09:28:51.260000Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:51.260000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StreamBench: Towards Benchmarking Continuous Improvement of Language Agents","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheng-Kuang Wu, Chieh-Yen Lin, Hung-yi Lee, Yun-Nung Chen, Zhi Rui Tam","submitted_at":"2024-06-13T02:08:28Z","abstract_excerpt":"Recent works have shown that large language model (LLM) agents are able to improve themselves from experience, which is an important ability for continuous enhancement post-deployment. However, existing benchmarks primarily evaluate their innate capabilities and do not assess their ability to improve over time. To address this gap, we introduce StreamBench, a pioneering benchmark designed to evaluate the continuous improvement of LLM agents over an input-feedback sequence. StreamBench simulates an online learning environment where LLMs receive a continuous flow of feedback stream and iterative"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08747","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/2406.08747/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":"2406.08747","created_at":"2026-07-05T09:28:51.260059+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.08747v2","created_at":"2026-07-05T09:28:51.260059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08747","created_at":"2026-07-05T09:28:51.260059+00:00"},{"alias_kind":"pith_short_12","alias_value":"WC2YVJNSA7IF","created_at":"2026-07-05T09:28:51.260059+00:00"},{"alias_kind":"pith_short_16","alias_value":"WC2YVJNSA7IF42VO","created_at":"2026-07-05T09:28:51.260059+00:00"},{"alias_kind":"pith_short_8","alias_value":"WC2YVJNS","created_at":"2026-07-05T09:28:51.260059+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20638","citing_title":"RIZZ: Routing Interactions to Near Zero-Interference Zones for Continual Adaptation of Black-Box Agents","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WC2YVJNSA7IF42VOUWDSSF42GJ","json":"https://pith.science/pith/WC2YVJNSA7IF42VOUWDSSF42GJ.json","graph_json":"https://pith.science/api/pith-number/WC2YVJNSA7IF42VOUWDSSF42GJ/graph.json","events_json":"https://pith.science/api/pith-number/WC2YVJNSA7IF42VOUWDSSF42GJ/events.json","paper":"https://pith.science/paper/WC2YVJNS"},"agent_actions":{"view_html":"https://pith.science/pith/WC2YVJNSA7IF42VOUWDSSF42GJ","download_json":"https://pith.science/pith/WC2YVJNSA7IF42VOUWDSSF42GJ.json","view_paper":"https://pith.science/paper/WC2YVJNS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.08747&json=true","fetch_graph":"https://pith.science/api/pith-number/WC2YVJNSA7IF42VOUWDSSF42GJ/graph.json","fetch_events":"https://pith.science/api/pith-number/WC2YVJNSA7IF42VOUWDSSF42GJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WC2YVJNSA7IF42VOUWDSSF42GJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WC2YVJNSA7IF42VOUWDSSF42GJ/action/storage_attestation","attest_author":"https://pith.science/pith/WC2YVJNSA7IF42VOUWDSSF42GJ/action/author_attestation","sign_citation":"https://pith.science/pith/WC2YVJNSA7IF42VOUWDSSF42GJ/action/citation_signature","submit_replication":"https://pith.science/pith/WC2YVJNSA7IF42VOUWDSSF42GJ/action/replication_record"}},"created_at":"2026-07-05T09:28:51.260059+00:00","updated_at":"2026-07-05T09:28:51.260059+00:00"}