1 citations · 2 across the 12 of their papers we have counts for
17 papers
EvoBelief: Falsifiable World Models for Self-Improving LLM Agents
Janet Wang, Jiang Guo, Yi Xiang +6
Self-evolving LLM agents typically improve how they act through accumulated experience, reflection, or skills. Yet even procedurally capable agents can fail when their beliefs abou…
VERSE: Verified Self-Evolving Optimizer for Agent Harnesses
Zekai Wang, Yingqiang Ge, Zekun Wang +6
Harness evolution improves an LLM agent's prompts, tools, and workflow, while the optimizer's own tools and procedures often remain fixed. We study whether an optimizer can improve…
Safety Must Survive Self-Improvement: Why Failures Persist and How Agents Recover
Yunbei Zhang, Janet Wang, Saiyue Lyu +5
Recursive self-improvement (RSI) allows agents to carry useful changes across generations. Maintaining safety across these generations involves both preventing unsafe behavior from…
Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems
Yunbei Zhang, Saiyue Lyu, Janet Wang +4
Multi-agent systems derive their capabilities from sharing evidence, delegating tasks, and combining information across agents. The same process creates a safety problem: contribut…
When Can Text Replace Vision? Structural Bottlenecks in Diagram Reasoning
Yunbei Zhang, Janet Wang, Jihun Hamm +1
Can structured text replace vision for diagram reasoning? A wrong answer after textualization can arise because the representation omits information the question needs, or because…
DRIFTLENS: Measuring Memory-Induced Reasoning Drift in Personalized Language Models
Xi Fang, Weijie Xu, Yingqiang Ge +3
Personalization changes what a model says to a user; we show that it can also change the reasoning trajectory used to justify the response. Modern LLMs personalize interactions by…
DNSMOS-C: Improving End-to-end Speech Quality Models via Contrastive Learning
Xinyu Liang, Fredrik Cumlin, Victor Ungureanu +3
We introduce DNSMOS-C, a compact end-to-end speech quality assessment model that extends the DNSMOS Pro framework by integrating a MOS-guided triplet-based contrastive loss. Applie…
LLM-ACES: Closed-Loop Discovery of Dynamical Systems with LLM-Guided Adaptive Search
Nikhil Abhyankar, Sha Li, Sanchit Kabra +3
Recovering governing Ordinary Differential Equations (ODEs) from data is a central challenge in modeling dynamical systems across scientific domains. Existing approaches cast disco…
Toward Individual Fairness Without Centralized Data: Selective Counterfactual Consistency for Vertical Federated Learning
Dawood Wasif, Chandan K. Reddy, Terrence J. Moore +1
When algorithmic decisions depend on data distributed across institutions, how can we ensure that an individual's outcome does not change arbitrarily based on a protected attribute…
Stop Comparing LLM Agents Without Disclosing the Harness
Yunbei Zhang, Janet Wang, Yingqiang Ge +3
This position paper argues that, for long-horizon tasks evaluated across models with comparable frontier capability, the agent execution harness, namely the infrastructure layer th…
Visual Exclusivity Attacks: Automatic Multimodal Red Teaming via Agentic Planning
Yunbei Zhang, Yingqiang Ge, Weijie Xu +3
Current multimodal red teaming treats images as wrappers for malicious payloads via typography or adversarial noise. These attacks are structurally brittle, as standard defenses ne…
Distractor Injection Attacks on Large Reasoning Models: Characterization and Defense
Zhehao Zhang, Weijie Xu, Shixian Cui +1
Recent advances in large reasoning models (LRMs) have enabled remarkable performance on complex tasks such as mathematics and coding by generating long Chain-of-Thought (CoT) trace…
The Personalization Trap: How User Memory Alters Emotional Reasoning in LLMs
Xi Fang, Weijie Xu, Yuchong Zhang +3
When an AI assistant remembers that Sarah is a single mother working two jobs, does it interpret her stress differently than if she were a wealthy executive? As personalized AI sys…
Quantifying Fairness in LLMs Beyond Tokens: A Semantic and Statistical Perspective
Weijie Xu, Yiwen Wang, Chi Xue +4
Large Language Models (LLMs) often generate responses with inherent biases, undermining their reliability in real-world applications. Existing evaluation methods often overlook bia…
DriveMind: A Dual Visual Language Model-based Reinforcement Learning Framework for Autonomous Driving
Dawood Wasif, Terrence J. Moore, Chandan K. Reddy +5
End-to-end autonomous driving systems map sensor data directly to control commands, but remain opaque, lack interpretability, and offer no formal safety guarantees. While recent vi…
SATA-BENCH: Select All That Apply Benchmark for Multiple Choice Questions
Weijie Xu, Shixian Cui, Xi Fang +3
Large language models (LLMs) are increasingly evaluated on single-answer multiple-choice tasks, yet many real-world problems require identifying all correct answers from a set of o…
FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning
Zhehao Zhang, Weijie Xu, Fanyou Wu +1
Safety alignment approaches in large language models (LLMs) often lead to the over-refusal of benign queries, significantly diminishing their utility in sensitive scenarios. To add…