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

arXiv:2604.08988v1 Announce Type: new Abstract: 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