works on
cross-domain context 1decision-aware modeling 1large language models 1online advertising 1reinforcement learning 1user simulation 1

From the 1 of 2 linked papers with an AI index.

most citedEvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfer

1 citations · 1 across the 2 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026★ 1 cited

EvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfer

Xingze Gao, Chuanrui Hu, Hongda Chen +9

Agent self-evolution in long-horizon LLM systems is largely procedural: useful experience is not merely stored information, but reusable procedures for searching, debugging, and ve…