43 citations · 57 across the 36 of their papers we have counts for
42 papers
Beyond Correct Answers: How Compositional Cues Shape Visual Judgments
Xiaoyu Ma, Zheyuan Zhang, Kaiwen Shi +1
Visual question answering requires models to assign attributes and relations to the correct objects, a problem known as visual binding. Structured prompts make these assignments ex…
Not Every User Says It All: Training Tool-Using Agents Beyond Ideal Simulated Users
Han Bao, Zheyuan Zhang, Kaiwen Shi +1
Tool-using agents are trained and evaluated almost exclusively with strong simulated users who state every detail clearly, yet real users are often weaker. We construct weak users…
Beyond Oracle Communication: Benchmarking Interactive Intent Alignment Under Miscommunication and Evolving User Intent
Zheyuan Zhang, Mengyuan Chao, Ke Xiao +5
Modern LLM agents increasingly tackle complex tasks through interactive, long-horizon exchanges with users, while existing benchmarks generally assume that users always accurately…
Continual Learning Mechanisms Compose for Long-Horizon Memorization
Zheyuan Zhang, Alvin Zhang, Daniel Khashabi +1
Language models may need to internalize information that arrives over time and retain it through many subsequent updates. To study this challenge, we introduce long-horizon memoriz…
Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning
Zheyuan Zhang, Manqing Mao, Hong Wang +8
Critic-free group-based reinforcement learning has become a scalable approach for post-training large language models. However, most existing methods allocate the same number of ro…
HoosierHelp: Benchmarking LLM Agents for Social Service Navigation
Yiyang Li, Weixiang Sun, Tianyi Ma +3
Social service navigation requires connecting help-seeking individuals to resources that satisfy their needs and specific constraints. Although LLM agents offer a promising interfa…
Confidence Laundering in Agent Systems: Why Uncertainty Needs a Latent Carrier
Kaiwen Shi, Zheyuan Zhang, Han Bao +2
Modern agent systems can turn uncertainty into overconfidence. Fragile upstream decisions are often exposed to downstream components as clean intermediate artifacts, while the unce…
SAGE: Answer-Conditioned Uncertainty Targets for Verbal Uncertainty Alignment
Kaiwen Shi, Zheyuan Zhang, Yanfang Ye
Large language models increasingly express uncertainty through natural-language statements, yet these expressions often fail to reflect the model's sampled behavior. We study verba…
Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization
Zheyuan Zhang, Kaiwen Shi, Han Bao +3
Post-training has become central to improving reasoning and alignment in large language models, where critic-free models enable scalable learning from model-generated outputs but l…
EvolveRouter: Co-Evolving Routing and Prompt for Multi-Agent Question Answering
Jiatan Huang, Zheyuan Zhang, Kaiwen Shi +2
Large language model agents often exhibit complementary strengths, making routing a promising approach for multi-agent question answering. However, existing routing methods remain…
BHyGNN+: Unsupervised Representation Learning for Heterophilic Hypergraphs
Tianyi Ma, Yiyue Qian, Zehong Wang +3
Hypergraph Neural Networks (HyGNNs) have demonstrated remarkable success in modeling higher-order relationships among entities. However, their performance often degrades on heterop…
OPBench: A Graph Benchmark to Combat the Opioid Crisis
Tianyi Ma, Yiyang Li, Yiyue Qian +4
The opioid epidemic continues to ravage communities worldwide, straining healthcare systems, disrupting families, and demanding urgent computational solutions. To combat this letha…
Drift-Bench: Diagnosing Cooperative Breakdowns in LLM Agents under Input Faults via Multi-Turn Interaction
Han Bao, Zheyuan Zhang, Pengcheng Jing +3
As Large Language Models transition to autonomous agents, user inputs frequently violate cooperative assumptions (e.g., implicit intent, missing parameters, false presuppositions,…
CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era
Kaiwen Shi, Weixiang Sun, Zheyuan Zhang +3
Scientific research relies on citation integrity, yet large language models (LLMs) have introduced a critical risk: fabricated references that appear plausible but correspond to no…
AI Alignment Breaks at the Edge
Han Bao, Yue Huang, Xiaoda Wang +5
General Alignment has improved average-case helpfulness and safety, but current alignment practice still rewards confident, single-turn responses. The problem is not only that mode…
Policy4OOD: A Knowledge-Guided World Model for Policy Intervention Simulation against the Opioid Overdose Crisis
Yijun Ma, Zehong Wang, Weixiang Sun +4
The opioid epidemic remains one of the most severe public health crises in the United States, yet evaluating policy interventions before implementation is difficult: multiple polic…
GLEN-Bench: A Graph-Language based Benchmark for Nutritional Health
Jiatan Huang, Zheyuan Zhang, Tianyi Ma +4
Nutritional interventions are important for managing chronic health conditions, but current computational methods provide limited support for personalized dietary guidance. We iden…
LongDA: Benchmarking LLM Agents for Long-Document Data Analysis
Yiyang Li, Zheyuan Zhang, Tianyi Ma +4
We introduce LongDA, a data analysis benchmark for evaluating LLM-based agents under documentation-intensive analytical workflows. In contrast to existing benchmarks that assume we…
BLURR: A Boosted Low-Resource Inference for Vision-Language-Action Models
Xiaoyu Ma, Zhengqing Yuan, Zheyuan Zhang +3
Vision-language-action (VLA) models enable impressive zero shot manipulation, but their inference stacks are often too heavy for responsive web demos or high frequency robot contro…
Interpretable Graph-Language Modeling for Detecting Youth Illicit Drug Use
Yiyang Li, Zehong Wang, Zhengqing Yuan +4
Illicit drug use among teenagers and young adults (TYAs) remains a pressing public health concern, with rising prevalence and long-term impacts on health and well-being. To detect…
NG-Router: Graph-Supervised Multi-Agent Collaboration for Nutrition Question Answering
Kaiwen Shi, Zheyuan Zhang, Zhengqing Yuan +4
Diet plays a central role in human health, and Nutrition Question Answering (QA) offers a promising path toward personalized dietary guidance and the prevention of diet-related chr…
MAPRO: Recasting Multi-Agent Prompt Optimization as Maximum a Posteriori Inference
Zheyuan Zhang, Lin Ge, Hongjiang Li +3
Large language models (LLMs) have demonstrated remarkable capabilities across diverse tasks, and LLM-based agents further extend these abilities to various practical workflows. Whi…
AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question Answering
Zheyuan Zhang, Kaiwen Shi, Zhengqing Yuan +6
Large language models (LLMs) and agent-based frameworks have advanced rapidly, enabling diverse applications. Yet, with the proliferation of models and agentic strategies, practiti…
Food4All: An Agentic Framework and Benchmark for Food Resource Navigation with Adaptive User Understanding
Yiyang Li, Weixiang Sun, Tianyi Ma +3
Food assistance referral requires conversational agents to translate underspecified, often noisy help-seeking dialogues into locally valid resource recommendations. We present Food…