2 papers
cs.AI2026
MetaExp: Learning to Self-Improve through Experience via Verifiable Cross-Task Environment Scaling
Renhao Li, Xinjie Shen, Yang Su +4
Language-model agents can accumulate interaction feedback, but reliably turning that feedback into reusable experience remains challenging. Existing methods either optimize externa…
cs.LG2026
E-Commerce Bench: Evaluating LLM Agents on Long-Horizon Autonomous Business Operation
Wei Fan, Xinjie Shen, Xudong Guo +8
Long-horizon agentic tasks go beyond chaining short tasks over more interaction turns. Their evolving dynamic environments and long-range dependencies require Large Language Models…