5 papers
MCTS-Judge: Test-Time Scaling in LLM-as-a-Judge for Code Correctness Evaluation
Yutong Wang, Pengliang Ji, Chaoqun Yang +4
The LLM-as-a-Judge paradigm shows promise for evaluating generative content but lacks reliability in reasoning-intensive scenarios, such as programming. Inspired by recent advances…
Beyond Policy Optimization: A Data Curation Flywheel for Sparse-Reward Long-Horizon Planning
Yutong Wang, Pengliang Ji, Kaixin Li +3
Large Language Reasoning Models have demonstrated remarkable success on static tasks, yet their application to multi-round agentic planning in interactive environments faces two fu…
Deploying Ten Thousand Robots: Scalable Imitation Learning for Lifelong Multi-Agent Path Finding
He Jiang, Yutong Wang, Rishi Veerapaneni +3
Lifelong Multi-Agent Path Finding (LMAPF) repeatedly finds collision-free paths for multiple agents that are continually assigned new goals when they reach current ones. Recently,…
ET-Plan-Bench: Embodied Task-level Planning Benchmark Towards Spatial-Temporal Cognition with Foundation Models
Lingfeng Zhang, Yuening Wang, Hongjian Gu +12
Recent advancements in Large Language Models (LLMs) have spurred numerous attempts to apply these technologies to embodied tasks, particularly focusing on high-level task planning…
LNS2+RL: Combining Multi-Agent Reinforcement Learning with Large Neighborhood Search in Multi-Agent Path Finding
Yutong Wang, Tanishq Duhan, Jiaoyang Li +1
Multi-Agent Path Finding (MAPF) is a critical component of logistics and warehouse management, which focuses on planning collision-free paths for a team of robots in a known enviro…