{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WC2YVJNSA7IF42VOUWDSSF42GJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8dc305769581aba0680a688c583317df7dd94f51b75d659c5f9c7cb36bf6b9b1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T02:08:28Z","title_canon_sha256":"ba86c64a394c5a8a602e4bbf94b3f0ef59ee833003138f9713f58f08331a7eca"},"schema_version":"1.0","source":{"id":"2406.08747","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08747","created_at":"2026-07-05T09:28:51Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08747v2","created_at":"2026-07-05T09:28:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08747","created_at":"2026-07-05T09:28:51Z"},{"alias_kind":"pith_short_12","alias_value":"WC2YVJNSA7IF","created_at":"2026-07-05T09:28:51Z"},{"alias_kind":"pith_short_16","alias_value":"WC2YVJNSA7IF42VO","created_at":"2026-07-05T09:28:51Z"},{"alias_kind":"pith_short_8","alias_value":"WC2YVJNS","created_at":"2026-07-05T09:28:51Z"}],"graph_snapshots":[{"event_id":"sha256:ed96615921978cd6d35086b076e7d457a18cc07001f500c384d1ad9792859e34","target":"graph","created_at":"2026-07-05T09:28:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.08747/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Cheng-Kuang Wu, Chieh-Yen Lin, Hung-yi Lee, Yun-Nung Chen, Zhi Rui Tam","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T02:08:28Z","title":"StreamBench: Towards Benchmarking Continuous Improvement of Language Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08747","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b0c8a0c9416000119977bdea42b3e888baf1ccf05675bacb243682576832463b","target":"record","created_at":"2026-07-05T09:28:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8dc305769581aba0680a688c583317df7dd94f51b75d659c5f9c7cb36bf6b9b1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T02:08:28Z","title_canon_sha256":"ba86c64a394c5a8a602e4bbf94b3f0ef59ee833003138f9713f58f08331a7eca"},"schema_version":"1.0","source":{"id":"2406.08747","kind":"arxiv","version":2}},"canonical_sha256":"b0b58aa5b207d05e6aaea58729179a32772e9b92002eb4a198502ab2e98b2c1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0b58aa5b207d05e6aaea58729179a32772e9b92002eb4a198502ab2e98b2c1b","first_computed_at":"2026-07-05T09:28:51.260000Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:51.260000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XBkinI4ygBqkAijUqmLN0PVcCL25yU505/E7althDjkHNR8rtwpqR1ytnypBsGkml76AcNLkFvU+yCqeGJ4TAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:51.260474Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.08747","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0c8a0c9416000119977bdea42b3e888baf1ccf05675bacb243682576832463b","sha256:ed96615921978cd6d35086b076e7d457a18cc07001f500c384d1ad9792859e34"],"state_sha256":"6f7dff9fbbb5d891f761a50cda6791bf0805b759d9d2b5091b857521756f72d3"}