4 papers · 1 filter
Learning from Unverified Peers via Shared Residual Distillation
Feiyang Chen, Runze Ma, Zichen Wang +4
A language model can generate several solutions to the same problem, some leading to correct answers and others to incorrect ones. Many post-training methods turn these trajectorie…
Jev-LiteMAS: Separating Decisions from Generation in Multi-Agent Workflows
Kaixiang Wang, Zhaijiacheng Zhou, Jiong Lou +1
Multi-agent LLM systems rely on generative models for expert execution, workflow planning, and artifact review. Yet many coordination operations require only bounded decisions, suc…
Deep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning Models
Hefeng Zhou, Jinxuan Zhang, Jiong Lou +4
The emergence of Chain-of-Thought (CoT) reasoning has significantly enhanced the ability of large language models (LLMs) to tackle complex, multi-step tasks. However, when errors o…
E-mem: Multi-agent based Episodic Context Reconstruction for LLM Agent Memory
Kaixiang Wang, Yidan Lin, Jiong Lou +3
The evolution of Large Language Model (LLM) agents towards System~2 reasoning, characterized by deliberative, high-precision problem-solving, requires maintaining rigorous logical…