2 papers
cs.CL2026
A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression
Jincheng Ren, Siwei Wu, Yizhi Li +8
As terminal agents scale to long-horizon, multi-turn workflows, a key bottleneck is not merely limited context length, but the accumulation of noisy terminal observations in the in…
cs.IR2026
Break the Optimization Barrier of LLM-Enhanced Recommenders: A Theoretical Analysis and Practical Framework
Zhangchi Zhu, Wei Zhang
Large language model (LLM)-enhanced recommendation models inject LLM representations into backbone recommenders to exploit rich item text without inference-time LLM cost. However,…