2 citations · 4 across the 21 of their papers we have counts for
23 papers
Ask, Relax, or Act? Evaluating Actionable Indeterminacy in LLM Preference Reasoning
Ang Li, Yue Lin, Feifei Kou +6
An LLM agent can recognize uncertainty yet still choose the wrong next step: asking when action is already justified, or seeking clarification when the constraints must change. We…
Solver-Guided Reasoning for Mixed-Equilibrium Strategies
Han Wang, Philippe Beardsell, Boning Li +4
Reasoning in large language models (LLMs) is often grounded in human text, human demonstrations, and human-generated rationales. For equilibrium reasoning in complex games, however…
From Economic Agents to Agentic Economies: A Systems Blueprint for Economic World Models
Jiale Han, Xiang Li, Jing Qian +7
Economic World Models (EWMs) are generative economic models that simulate how economies evolve from within by modeling heterogeneous agents, their beliefs and actions, and the mark…
Healthcare Mechanisms from Policy-as-Code Search under Strategic Provider Response
Zihan Wang, Xiang Xu, Hongyuan Zha +1
Healthcare mechanisms are inseparable from the strategic provider response they induce: existing healthcare AI benchmarks hold this response fixed and so cannot evaluate mechanisms…
Agentifying Patient Dynamics within LLMs through Interacting with Clinical World Model
Minghao Wu, Yuting Yan, Zhenyang Cai +9
Sepsis management in the ICU requires sequential treatment decisions under rapidly evolving patient physiology. Although large language models (LLMs) encode broad clinical knowledg…
The Reciprocity Gradient
Yue Lin, Pascal Poupart, Shuhui Zhu +5
Communication is fundamental to sustaining reciprocity and cooperation in strategic interactions. We identify and formulate the influence attribution problem as the central optimiz…
Epistemic Gain, Aleatoric Cost: Uncertainty Decomposition in Multi-Agent Debate for Math Reasoning
Dan Qiao, Binbin Chen, Fengyu Cai +7
Multi-Agent Debate (MAD) has shown promise in improving reasoning and reducing hallucinations, yet it remains unclear how information exchange shapes individual reasoning behavior.…
Talk, Judge, Cooperate: Gossip-Driven Indirect Reciprocity in Self-Interested LLM Agents
Shuhui Zhu, Yue Lin, Shriya Kaistha +5
Indirect reciprocity, which means helping those who have helped others, is difficult to sustain among decentralized, self-interested LLM agents without reliable reputation systems.…
Policy-Conditioned Policies for Multi-Agent Task Solving
Yue Lin, Shuhui Zhu, Wenhao Li +5
In multi-agent tasks, the central challenge lies in the dynamic adaptation of strategies. However, directly conditioning on opponents' strategies is intractable in the prevalent de…
CALM Before the STORM: Unlocking Native Reasoning for Optimization Modeling
Zhengyang Tang, Zihan Ye, Chenyu Huang +9
Large Reasoning Models (LRMs) have demonstrated strong capabilities in complex multi-step reasoning, opening new opportunities for automating optimization modeling. However, existi…
TextAtari: 100K Frames Game Playing with Language Agents
Wenhao Li, Wenwu Li, Chuyun Shen +8
We present TextAtari, a benchmark for evaluating language agents on very long-horizon decision-making tasks spanning up to 100,000 steps. By translating the visual state representa…
Information Bargaining: Bilateral Commitment in Bayesian Persuasion
Yue Lin, Shuhui Zhu, William A Cunningham +4
Bayesian persuasion, an extension of cheap-talk communication, involves an informed sender committing to a signaling scheme to influence a receiver's actions. Compared to cheap tal…
Offline Multi-agent Reinforcement Learning via Sequential Score Decomposition
Dan Qiao, Wenhao Li, Shanchao Yang +2
Offline cooperative multi-agent reinforcement learning (MARL) faces unique challenges due to distributional shifts, particularly stemming from the high dimensionality of joint acti…
Class-Conditional Neural Polarizer: A Lightweight and Effective Backdoor Defense by Purifying Poisoned Features
Mingli Zhu, Shaokui Wei, Hongyuan Zha +1
Recent studies have highlighted the vulnerability of deep neural networks to backdoor attacks, where models are manipulated to rely on embedded triggers within poisoned samples, de…
Revisiting the Auxiliary Data in Backdoor Purification
Shaokui Wei, Shanchao Yang, Jiayin Liu +1
Backdoor attacks occur when an attacker subtly manipulates machine learning models during the training phase, leading to unintended behaviors when specific triggers are present. To…
Verbalized Bayesian Persuasion
Wenhao Li, Yue Lin, Xiangfeng Wang +3
Information design (ID) explores how a sender influence the optimal behavior of receivers to achieve specific objectives. While ID originates from everyday human communication, exi…
Backdoor Mitigation by Distance-Driven Detoxification
Shaokui Wei, Jiayin Liu, Hongyuan Zha
Backdoor attacks undermine the integrity of machine learning models by allowing attackers to manipulate predictions using poisoned training data. Such attacks lead to targeted misc…
Carbon Market Simulation with Adaptive Mechanism Design
Han Wang, Wenhao Li, Hongyuan Zha +1
A carbon market is a market-based tool that incentivizes economic agents to align individual profits with the global utility, i.e., reducing carbon emissions to tackle climate chan…
Transfer Learning for Diffusion Models
Yidong Ouyang, Liyan Xie, Hongyuan Zha +1
Diffusion models, a specific type of generative model, have achieved unprecedented performance in recent years and consistently produce high-quality synthetic samples. A critical p…
Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
Shaokui Wei, Hongyuan Zha, Baoyuan Wu
Data-poisoning backdoor attacks are serious security threats to machine learning models, where an adversary can manipulate the training dataset to inject backdoors into models. In…
Can language agents be alternatives to PPO? A Preliminary Empirical Study On OpenAI Gym
Junjie Sheng, Zixiao Huang, Chuyun Shen +5
The formidable capacity for zero- or few-shot decision-making in language agents encourages us to pose a compelling question: Can language agents be alternatives to PPO agents in t…
A Variational Autoencoder for Neural Temporal Point Processes with Dynamic Latent Graphs
Sikun Yang, Hongyuan Zha
Continuously-observed event occurrences, often exhibit self- and mutually-exciting effects, which can be well modeled using temporal point processes. Beyond that, these event dynam…
Score Matching-based Pseudolikelihood Estimation of Neural Marked Spatio-Temporal Point Process with Uncertainty Quantification
Zichong Li, Qunzhi Xu, Zhenghao Xu +3
Spatio-temporal point processes (STPPs) are potent mathematical tools for modeling and predicting events with both temporal and spatial features. Despite their versatility, most ex…