40 citations · 46 across the 20 of their papers we have counts for
21 papers
VIEWCRAFT: Evolving What Multimodal Agents See and How They Read It
Binxiao Xu, Ruichuan An, Bocheng Zou +7
Reusable skills improve multimodal agents without updating model weights, but their effectiveness depends on both the evidence presented and the procedure used to read it. We intro…
HarnessEval-W: Agentifying the Evaluation of Visual Worlds
Weiliang Chen, Haowen Sun, Jun Gao +40
A benchmark should deliver more than a scalar score: what makes an evaluation trustworthy is the reasoning that justifies the score. This is especially critical for world models, w…
OdysSim: Building Foundation Models for Human Behavior Simulation
Xuhui Zhou, Weiwei Sun, Weihua Du +6
Large language models are increasingly deployed as human simulators for interactive evaluation and social simulation. Yet helpfulness-driven post-training pulls them toward a homog…
Reinforcing Human Behavior Simulation via Verbal Feedback
Weiwei Sun, Xuhui Zhou, Jiarui Liu +13
Humans learn social norms and behaviors from verbal feedback (e.g., a parent saying "that was rude" or a friend explaining "here's why that hurt"). Yet, learning from feedback for…
Why Search When You Can Transfer? Amortized Agentic Workflow Design from Structural Priors
Shiyi Du, Jiayuan Liu, Weihua Du +6
Automated agentic workflow design currently relies on per-task iterative search, which is computationally prohibitive and fails to reuse structural knowledge across tasks. We obser…
The Consensus Trap: Rescuing Multi-Agent LLMs from Adversarial Majorities via Token-Level Collaboration
Jiayuan Liu, Shiyi Du, Weihua Du +2
Multi-agent large language model (LLM) architectures increasingly rely on response-level aggregation, such as Majority Voting (MAJ), to raise reasoning ceilings. However, in open e…
AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation
Weihua Du, Jingming Zhuo, Yixin Dong +9
Recent large language model (LLM) agents have shown promise in using execution feedback for test-time adaptation. However, robust self-improvement remains far from solved: most app…
Mind the Sim2Real Gap in User Simulation for Agentic Tasks
Xuhui Zhou, Weiwei Sun, Qianou Ma +8
As NLP evaluation shifts from static benchmarks to multi-turn interactive settings, LLM-based simulators have become widely used as user proxies, serving two roles: generating user…
GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning
Ningyuan Yang, Weihua Du, Weiwei Sun +2
Reinforcement learning (RL) has become a central post-training paradigm for large language models (LLMs), but its performance is highly sensitive to the quality of training problem…
Training Proactive and Personalized LLM Agents
Weiwei Sun, Xuhui Zhou, Weihua Du +5
Despite rapid progress, current AI agents are primarily optimized for isolated task completion. We argue for a paradigm shift toward training agents as collaborators that communica…
Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
Miao Lu, Weiwei Sun, Weihua Du +4
We study reinforcement learning (RL) fine-tuning of large language model (LLM) agents for long-horizon multi-turn tool use, where context length quickly becomes a fundamental bottl…
Generalizable End-to-End Tool-Use RL with Synthetic CodeGym
Weihua Du, Hailei Gong, Zhan Ling +7
Tool-augmented large language models (LLMs), hereafter LLM agents, leverage external tools to solve diverse tasks and interface with the real world. However, current training pract…
Agentic-R1: Distilled Dual-Strategy Reasoning
Weihua Du, Pranjal Aggarwal, Sean Welleck +1
Current long chain-of-thought (long-CoT) models excel at mathematical reasoning but rely on slow and error-prone natural language traces. Tool-augmented agents address arithmetic v…
ZeroTuning: Unlocking the Initial Token's Power to Enhance Large Language Models Without Training
Feijiang Han, Xiaodong Yu, Jianheng Tang +3
Token-level attention tuning, a class of training-free methods including Post-hoc Attention Steering (PASTA) and Attention Calibration (ACT), has emerged as a promising approach fo…
Optimizing Temperature for Language Models with Multi-Sample Inference
Weihua Du, Yiming Yang, Sean Welleck
Multi-sample aggregation strategies, such as majority voting and best-of-N sampling, are widely used in contemporary large language models (LLMs) to enhance predictive accuracy acr…
Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence Challenge
Weihua Du, Qiushi Lyu, Jiaming Shan +8
We introduce Constrained Human-AI Cooperation (CHAIC), an inclusive embodied social intelligence challenge designed to test social perception and cooperation in embodied agents. In…
HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments
Qinhong Zhou, Sunli Chen, Yisong Wang +6
Recent advances in high-fidelity virtual environments serve as one of the major driving forces for building intelligent embodied agents to perceive, reason and interact with the ph…
T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step
Zehui Chen, Weihua Du, Wenwei Zhang +8
Large language models (LLM) have achieved remarkable performance on various NLP tasks and are augmented by tools for broader applications. Yet, how to evaluate and analyze the tool…
Iteratively Learn Diverse Strategies with State Distance Information
Wei Fu, Weihua Du, Jingwei Li +3
In complex reinforcement learning (RL) problems, policies with similar rewards may have substantially different behaviors. It remains a fundamental challenge to optimize rewards wh…
Building Cooperative Embodied Agents Modularly with Large Language Models
Hongxin Zhang, Weihua Du, Jiaming Shan +5
In this work, we address challenging multi-agent cooperation problems with decentralized control, raw sensory observations, costly communication, and multi-objective tasks instanti…
Automatic Truss Design with Reinforcement Learning
Weihua Du, Jinglun Zhao, Chao Yu +7
Truss layout design, namely finding a lightweight truss layout satisfying all the physical constraints, is a fundamental problem in the building industry. Generating the optimal la…