SEA-Eval: A Benchmark for Evaluating Self-Evolving Agents Beyond Episodic Assessment

Computer Science > Artificial Intelligence [Submitted on 10 Apr 2026] SEA-Eval: A Benchmark for Evaluating Self-Evolving Agents Beyond Episodic Assessment Sihang Jiang, Lipeng Ma, Zhonghua Hong, Keyi Wang, Zhiyu Lu, Shisong Chen, Jinghao Zhang, Tianjun Pan, Weijia Zhou, Jiaqing Liang, Yanghua Xiao Current LLM-based agents demonstrate strong performance in episodic task execution but remain constrained by static toolsets and episodic amnesia, failing to accumulate experience or optimize strategies across task boundaries. While the Self-Evolving Agent (SEA) paradigm has been previously proposed, this paper contributes a new formal definition of SEA grounded in digital embodiment and continuous cross-task evolution, and introduces SEA-Eval, the first benchmark designed to evaluate SEA characteristics across two dimensions, intra-task execution reliability and long-term evolutionary performance. By organizing tasks into sequential streams and analyzing Success Rate and Token Consumption over time, SEA-Eval quantifies evolutionary gain and structural stability in ways that existing episodic benchmarks cannot. Empirical evaluations reveal a significant evolutionary bottleneck in current state-of-the-art frameworks, where identical success rates mask up to 31.2 times differences in token consumption and divergent evolutionary trajectories under sequential analysis. SEA-Eval provides a rigorous scientific foundation for advancing agents from mere task executors toward genuinely self-evolving digital entities. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2604.08988 [cs.AI]   (or arXiv:2604.08988v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.08988 Focus to learn more Submission history From: Sihang Jiang [view email] [v1] Fri, 10 Apr 2026 05:49:50 UTC (11,637 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)