14 papers
JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting
Lanxiang Hu, Zhaoxiang Feng, Yulun Wu +9
Speculative decoding (SD) accelerates autoregressive Large Language Models (LLMs) by drafting multiple tokens and verifying them in parallel, but it faces a scaling limitation: inc…
AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications
Yujie Zhao, Boqin Yuan, Junbo Huang +9
Large Language Models (LLMs) are increasingly used as autonomous agents in complex, long-horizon applications, where effective memory is critical for sustained performance. Yet exi…
AgentKVShift: Efficient KV Cache Reuse for Agentic Memory Systems
Nilesh Prasad Pandey, Jason Kong, Lanxiang Hu +5
Memory-augmented LLM agents maintain context across hundreds of interactions through agentic memory systems that actively curate retrieved content with LLM-generated metadata such…
Does Tone Change the Answer? Evaluating Prompt Politeness Effects on Modern LLMs: GPT, Gemini, and LLaMA
Hanyu Cai, Binqi Shen, Lier Jin +2
Prompt engineering has emerged as a critical factor influencing large language model (LLM) performance, yet the impact of pragmatic elements such as linguistic tone and politeness…
d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation
Yu-Yang Qian, Junda Su, Lanxiang Hu +4
Diffusion large language models (dLLMs) offer capabilities beyond those of autoregressive (AR) LLMs, such as parallel decoding and random-order generation. However, realizing these…
Stronger-MAS: Multi-Agent Reinforcement Learning for Collaborative LLMs
Yujie Zhao, Lanxiang Hu, Yang Wang +4
Multi-agent systems (MAS) and reinforcement learning (RL) are widely used to enhance the agentic capabilities of large language models (LLMs). MAS improves task performance through…