Skip to content
arXiv cs.AI · Papers

ECHO: Prune To Act, Trace To Learn With Selective Turn Memory In Agentic RL

arXiv:2606.31650v2 Announce Type: replace-cross Abstract: Long-horizon language agents must repeatedly interact with tools, accumulate evidence, and make decisions under bounded context windows. Context-management methods make such rollouts feasible by simplifying past interactions through deletion, folding, or memory