{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TTBHFXIC2PVHVIXCUURUV45JNW","short_pith_number":"pith:TTBHFXIC","schema_version":"1.0","canonical_sha256":"9cc272dd02d3ea7aa2e2a5234af3a96d8ab28b3e17ec34d20104bee559ceb291","source":{"kind":"arxiv","id":"2608.00155","version":1},"attestation_state":"computed","paper":{"title":"AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dapeng Hu, Dong Yan, Jian Liang, Nicholas Jing Yuan, Qi Zhang, Ran He, Tieniu Tan","submitted_at":"2026-07-31T17:50:08Z","abstract_excerpt":"Large language model (LLM) agents can self-evolve by continually improving from their own accumulated experience. However, existing studies predominantly adopt independent evaluation. Consequently, the behavior of self-evolving agents in realistic streaming settings, where agents adapt to diverse and complex task streams, remains poorly understood. To address this gap, we introduce AgentStream, a unified framework that evaluates self-evolving agents spanning diverse evolution components by organizing agentic benchmarks into a configurable task stream and instantiating the \\texttt{Isolated}, \\t"},"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":"2608.00155","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-31T17:50:08Z","cross_cats_sorted":[],"title_canon_sha256":"b1ef3a9fef84cd82c66570bdc03e514dd5982d6c1bbc403c1da5614960f29729","abstract_canon_sha256":"cd97df23617401f181cecf0d8d1486196340524757df8100ebc764e4121832f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:33:05.422226Z","signature_b64":"WOPPPp52H/Jo2Df+sjLhAsFxWTXfY2DHpHEXEW4Ibjat7diizzssF9mdME7JkMFfvLtTlPhe/jzuzmyzC4wnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cc272dd02d3ea7aa2e2a5234af3a96d8ab28b3e17ec34d20104bee559ceb291","last_reissued_at":"2026-08-04T00:33:05.420801Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:33:05.420801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dapeng Hu, Dong Yan, Jian Liang, Nicholas Jing Yuan, Qi Zhang, Ran He, Tieniu Tan","submitted_at":"2026-07-31T17:50:08Z","abstract_excerpt":"Large language model (LLM) agents can self-evolve by continually improving from their own accumulated experience. However, existing studies predominantly adopt independent evaluation. Consequently, the behavior of self-evolving agents in realistic streaming settings, where agents adapt to diverse and complex task streams, remains poorly understood. To address this gap, we introduce AgentStream, a unified framework that evaluates self-evolving agents spanning diverse evolution components by organizing agentic benchmarks into a configurable task stream and instantiating the \\texttt{Isolated}, \\t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00155","kind":"arxiv","version":1},"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/2608.00155/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":"2608.00155","created_at":"2026-08-04T00:33:05.421896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00155v1","created_at":"2026-08-04T00:33:05.421896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00155","created_at":"2026-08-04T00:33:05.421896+00:00"},{"alias_kind":"pith_short_12","alias_value":"TTBHFXIC2PVH","created_at":"2026-08-04T00:33:05.421896+00:00"},{"alias_kind":"pith_short_16","alias_value":"TTBHFXIC2PVHVIXC","created_at":"2026-08-04T00:33:05.421896+00:00"},{"alias_kind":"pith_short_8","alias_value":"TTBHFXIC","created_at":"2026-08-04T00:33:05.421896+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/TTBHFXIC2PVHVIXCUURUV45JNW","json":"https://pith.science/pith/TTBHFXIC2PVHVIXCUURUV45JNW.json","graph_json":"https://pith.science/api/pith-number/TTBHFXIC2PVHVIXCUURUV45JNW/graph.json","events_json":"https://pith.science/api/pith-number/TTBHFXIC2PVHVIXCUURUV45JNW/events.json","paper":"https://pith.science/paper/TTBHFXIC"},"agent_actions":{"view_html":"https://pith.science/pith/TTBHFXIC2PVHVIXCUURUV45JNW","download_json":"https://pith.science/pith/TTBHFXIC2PVHVIXCUURUV45JNW.json","view_paper":"https://pith.science/paper/TTBHFXIC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00155&json=true","fetch_graph":"https://pith.science/api/pith-number/TTBHFXIC2PVHVIXCUURUV45JNW/graph.json","fetch_events":"https://pith.science/api/pith-number/TTBHFXIC2PVHVIXCUURUV45JNW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TTBHFXIC2PVHVIXCUURUV45JNW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TTBHFXIC2PVHVIXCUURUV45JNW/action/storage_attestation","attest_author":"https://pith.science/pith/TTBHFXIC2PVHVIXCUURUV45JNW/action/author_attestation","sign_citation":"https://pith.science/pith/TTBHFXIC2PVHVIXCUURUV45JNW/action/citation_signature","submit_replication":"https://pith.science/pith/TTBHFXIC2PVHVIXCUURUV45JNW/action/replication_record"}},"created_at":"2026-08-04T00:33:05.421896+00:00","updated_at":"2026-08-04T00:33:05.421896+00:00"}