13 papers
SceneSelect: Selective Learning for Trajectory Scene Classification and Expert Scheduling
Xinrun Wang, Deshun Xia, Yuxi Sun +1
Accurate trajectory prediction is fundamentally challenging due to high scene heterogeneity - the severe variance in motion velocity, spatial density, and interaction patterns acro…
The Agent Use of Agent Beings: Agent Cybernetics Is the Missing Science of Foundation Agents
Xinrun Wang, Chang Yang, He Zhao +2
LLM-based foundation agents that perceive, reason, and act across thousands of reasoning steps are rapidly becoming the dominant paradigm for deploying artificial intelligence in o…
SCALER:Synthetic Scalable Adaptive Learning Environment for Reasoning
Caijun Xu, Changyi Xiao, Zhongyuan Peng +2
Reinforcement learning (RL) offers a principled way to enhance the reasoning capabilities of large language models, yet its effectiveness hinges on training signals that remain inf…
LLM-Based World Models Can Make Decisions Solely, But Rigorous Evaluations are Needed
Chang Yang, Xinrun Wang, Junzhe Jiang +2
World model emerges as a key module in decision making, where MuZero and Dreamer achieve remarkable successes in complex tasks. Recent work leverages Large Language Models (LLMs) a…
Nondeterministic Polynomial-time Problem Challenge: An Ever-Scaling Reasoning Benchmark for LLMs
Chang Yang, Ruiyu Wang, Junzhe Jiang +9
Reasoning is the fundamental capability of large language models (LLMs). Due to the rapid progress of LLMs, there are two main issues of current benchmarks: i) these benchmarks can…
Graph-based Agent Memory: Taxonomy, Techniques, and Applications
Chang Yang, Chuang Zhou, Yilin Xiao +15
Memory emerges as the core module in the Large Language Model (LLM)-based agents for long-horizon complex tasks (e.g., multi-turn dialogue, game playing, scientific discovery), whe…