Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
TAP: Efficient Long-Horizon Agent Pruning via Trajectory-Anchored Recovery
Yuanzhe Li, Pengxin Wang, Yuxin Ren +5
Emerging long-horizon agentic tasks require repeated model calls, worsening the inference cost of already-costly language models. While narrow agentic tasks suggest potential for a…
cs.LG2026
GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs
Jianing Deng, Song Wang, Dongwei Wang +4
Mixture-of-Experts Large Language Models (MoE-LLMs) achieve strong performance but incur substantial memory overhead due to massive expert parameters. Mixed-precision quantization…