{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RCF65HK36IPNXMUMKNPK36CCGZ","short_pith_number":"pith:RCF65HK3","schema_version":"1.0","canonical_sha256":"888bee9d5bf21edbb28c535eadf8423679e0bbad79c4da371aa9d912cd88008f","source":{"kind":"arxiv","id":"2604.08988","version":3},"attestation_state":"computed","paper":{"title":"SEA-Eval: A Benchmark for Evaluating Self-Evolving Agents Beyond Episodic Assessment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Success rate alone creates a capability illusion for LLM agents, while the sequential convergence of token consumption distinguishes genuine self-evolution from pseudo-evolution.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiaqing Liang, Jinghao Zhang, Keyi Wang, Lipeng Ma, Shisong Chen, Sihang Jiang, Tengfei Wang, Tianjun Pan, Weijia Li, Yanghua Xiao, Zhiyu Lu, Zhonghua Hong","submitted_at":"2026-04-10T05:49:50Z","abstract_excerpt":"Current LLM-based agents demonstrate strong performance in episodic task execution but remain constrained by static toolsets and episodic amnesia, failing to accumulate experience across task boundaries. This paper formalizes the Self-Evolving Agent (SEA) from the perspective of digital embodiment and continuous cross-task evolution, introduces the Evolutionary Flywheel as its minimal sufficient architecture, and presents SEA-Eval -- the first benchmark designed specifically for evaluating SEAs. Grounded in Flywheel theory, SEA-Eval establishes SR and T as primary metrics and, through sequenti"},"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":true},"canonical_record":{"source":{"id":"2604.08988","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-10T05:49:50Z","cross_cats_sorted":[],"title_canon_sha256":"91bcea8d3ea6453766ce8714ab436ac17368eb54a20d24573fc0b71276e4b085","abstract_canon_sha256":"25c4bca7fb3ad2de5949922b4df69798dfc61a08ba3dfd00145975b327d6836f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:29.708905Z","signature_b64":"XeINiZGR0LU3D5Ck11vkudxvrUV07mN8Zwvwv2fX3JFCr+TeevvDfKksuQZ1Mx9A24Wsr3WTLwahqdIy2BjCDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"888bee9d5bf21edbb28c535eadf8423679e0bbad79c4da371aa9d912cd88008f","last_reissued_at":"2026-05-26T01:03:29.708097Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:29.708097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEA-Eval: A Benchmark for Evaluating Self-Evolving Agents Beyond Episodic Assessment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Success rate alone creates a capability illusion for LLM agents, while the sequential convergence of token consumption distinguishes genuine self-evolution from pseudo-evolution.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiaqing Liang, Jinghao Zhang, Keyi Wang, Lipeng Ma, Shisong Chen, Sihang Jiang, Tengfei Wang, Tianjun Pan, Weijia Li, Yanghua Xiao, Zhiyu Lu, Zhonghua Hong","submitted_at":"2026-04-10T05:49:50Z","abstract_excerpt":"Current LLM-based agents demonstrate strong performance in episodic task execution but remain constrained by static toolsets and episodic amnesia, failing to accumulate experience across task boundaries. This paper formalizes the Self-Evolving Agent (SEA) from the perspective of digital embodiment and continuous cross-task evolution, introduces the Evolutionary Flywheel as its minimal sufficient architecture, and presents SEA-Eval -- the first benchmark designed specifically for evaluating SEAs. Grounded in Flywheel theory, SEA-Eval establishes SR and T as primary metrics and, through sequenti"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"under identical success rates, token consumption differs by up to 31.2× across frameworks, with divergent evolutionary trajectories under sequential analysis -- demonstrating that success rate alone creates a capability illusion and that the sequential convergence of T is the key criterion for distinguishing genuine evolution from pseudo-evolution.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the sequential task stream design in SEA-Eval enables independent quantification of evolutionary gain, stability, and alignment without confounding from task similarity, agent initialization, or unstated priors in the Flywheel architecture.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SEA-Eval is the first benchmark for self-evolving agents that uses sequential tasks to show success rate alone misleads while convergence in token efficiency T distinguishes genuine evolution.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Success rate alone creates a capability illusion for LLM agents, while the sequential convergence of token consumption distinguishes genuine self-evolution from pseudo-evolution.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"db6caf6fbe4016db007fa5dd53f282b14c8c600035e1eaaa8e3d05d47dcbb344"},"source":{"id":"2604.08988","kind":"arxiv","version":3},"verdict":{"id":"22a8fe45-74b0-4695-bac5-298eec0eeba1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T17:48:15.540110Z","strongest_claim":"under identical success rates, token consumption differs by up to 31.2× across frameworks, with divergent evolutionary trajectories under sequential analysis -- demonstrating that success rate alone creates a capability illusion and that the sequential convergence of T is the key criterion for distinguishing genuine evolution from pseudo-evolution.","one_line_summary":"SEA-Eval is the first benchmark for self-evolving agents that uses sequential tasks to show success rate alone misleads while convergence in token efficiency T distinguishes genuine evolution.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the sequential task stream design in SEA-Eval enables independent quantification of evolutionary gain, stability, and alignment without confounding from task similarity, agent initialization, or unstated priors in the Flywheel architecture.","pith_extraction_headline":"Success rate alone creates a capability illusion for LLM agents, while the sequential convergence of token consumption distinguishes genuine self-evolution from pseudo-evolution."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.08988/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":2,"snapshot_sha256":"4871c66d70ec8ad33fb3e7069cad3e31d39cde3acad81e229eaad8a868c43bab"},"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":"2604.08988","created_at":"2026-05-26T01:03:29.708213+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.08988v3","created_at":"2026-05-26T01:03:29.708213+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.08988","created_at":"2026-05-26T01:03:29.708213+00:00"},{"alias_kind":"pith_short_12","alias_value":"RCF65HK36IPN","created_at":"2026-05-26T01:03:29.708213+00:00"},{"alias_kind":"pith_short_16","alias_value":"RCF65HK36IPNXMUM","created_at":"2026-05-26T01:03:29.708213+00:00"},{"alias_kind":"pith_short_8","alias_value":"RCF65HK3","created_at":"2026-05-26T01:03:29.708213+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RCF65HK36IPNXMUMKNPK36CCGZ","json":"https://pith.science/pith/RCF65HK36IPNXMUMKNPK36CCGZ.json","graph_json":"https://pith.science/api/pith-number/RCF65HK36IPNXMUMKNPK36CCGZ/graph.json","events_json":"https://pith.science/api/pith-number/RCF65HK36IPNXMUMKNPK36CCGZ/events.json","paper":"https://pith.science/paper/RCF65HK3"},"agent_actions":{"view_html":"https://pith.science/pith/RCF65HK36IPNXMUMKNPK36CCGZ","download_json":"https://pith.science/pith/RCF65HK36IPNXMUMKNPK36CCGZ.json","view_paper":"https://pith.science/paper/RCF65HK3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.08988&json=true","fetch_graph":"https://pith.science/api/pith-number/RCF65HK36IPNXMUMKNPK36CCGZ/graph.json","fetch_events":"https://pith.science/api/pith-number/RCF65HK36IPNXMUMKNPK36CCGZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RCF65HK36IPNXMUMKNPK36CCGZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RCF65HK36IPNXMUMKNPK36CCGZ/action/storage_attestation","attest_author":"https://pith.science/pith/RCF65HK36IPNXMUMKNPK36CCGZ/action/author_attestation","sign_citation":"https://pith.science/pith/RCF65HK36IPNXMUMKNPK36CCGZ/action/citation_signature","submit_replication":"https://pith.science/pith/RCF65HK36IPNXMUMKNPK36CCGZ/action/replication_record"}},"created_at":"2026-05-26T01:03:29.708213+00:00","updated_at":"2026-05-26T01:03:29.708213+00:00"}