8 citations · 25 across the 39 of their papers we have counts for
41 papers
Grid-Bench: Can LLMs Predict How Discrete Worlds Change?
Zixiang Xu, Zirui Song, Wanrong Zheng +16
Spatial instructions describe how to move objects, transform regions, or modify their surroundings. When several operations are applied in sequence, each acts on a configuration sh…
EAIR: Interaction Risks in Enterprise LLM Multi-Agent Systems
Yuchen Ma, Swadheen Shukla, Paulo Salem +5
LLM agents increasingly divide enterprise work across roles with different goals, authority, access, and information. Because each agent often sees only a local snapshot of the ent…
Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives
Zheyuan Liu, Weiliang Zhao, Xiangchi Yuan +3
Large language models are increasingly deployed as autonomous agents serving users on behalf of companies, placing them in settings where user and deployer interests can conflict.…
Forgotten in Weights, Recovered by Tools: Agentic Tool Unlearning for LLM Agents
Baicheng Chen, Zheyuan Liu, Jingyu Zhang +4
Large language models (LLMs) are increasingly deployed as tool-augmented agents, where responses can depend on tool calls and external observations rather than model parameters alo…
Learning from Synthetic Data without Model Collapse in Iterative Instruction Tuning
Xiaonan Luo, Yue Huang, Kehan Guo +4
Model collapse is a central challenge in learning from synthetic data: as later-generation large language models (LLMs) are trained on an increasing proportion of model-generated d…
MemoHarness: Agent Harnesses That Learn from Experience
Yue Huang, Wenjie Wang, Han Bao +7
An agent harness is the external control layer that turns a base LLM into an executable agent by managing context, tools, orchestration, memory, decoding, and output handling. Whil…
UXBench: Measuring the Actionability of LLM-Generated UX Critiques
Wenjie Wang, Yue Huang, Zipeng Ling +11
Large language models (LLMs) are increasingly deployed as UX judges that inspect interfaces, diagnose usability problems, and propose repairs. Yet no controlled benchmark measures…
Reward Transport: Property Control in Flow Matching via Noise-Space Alignment
Kehan Guo, Yili Shen, Yujun Zhou +4
The coupling in flow matching -- the rule pairing noise vectors with data points -- is typically treated as a computational choice. We show that this coupling can instead serve as…
Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents
Yujun Zhou, Kehan Guo, Haomin Zhuang +8
Interactive LLM agents are becoming part of daily work, but they do not reliably become easier to work with over time: a correction remembered in one session may still be violated…
T2J-BENCH: Benchmarking Coding Agents on Execution-Grounded PyTorch-to-JAX Repository Migration
Tao Feng, Linxin Song, Jiefeng Chen +9
Migrating a machine-learning codebase across frameworks--for example from PyTorch to JAX--is a routine but costly engineering task that is fundamentally cross-paradigm: eager, stat…
SpecAlign: Efficient Specification-Grounded Alignment of Large Language Models via Synthetic Data
Wenjie Wang, Yue Huang, Zhengqing Yuan +6
As large language models (LLMs) are increasingly deployed in real-world applications, alignment is no longer governed by a single universal notion of safety or helpfulness, but ins…
DOG-DPO:Dynamic Optimization in Geometry for Safety Alignment
Yi Nian, Tiankai Yang, Yudi Zhang +7
Safety alignment for large language models relies on preference data, but current pipelines often train on large, redundant datasets. Existing data selection methods typically scor…
JobBench: Aligning Agent Work With Human Will
Yuetai Li, Yichen Feng, Zhangchen Xu +21
Current benchmarks for occupational AI agents are scoped primarily by economic values, telling a replacement story. We introduce JobBench, which evaluates AI agents on the workflow…
Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions
Diancheng Kang, Zheyuan Liu, Ningshan Ma +3
Activation steering controls language model behavior by adding directions to internal representations at inference time, but standard residual-stream steering can fail in stateful…
AgentTrap: Measuring Runtime Trust Failures in Third-Party Agent Skills
Haomin Zhuang, Hanwen Xing, Yujun Zhou +5
Third-party skills are becoming the package ecosystem for LLM agents. They package natural-language instructions, helper scripts, templates, documents, and service configuration in…
Visual Aesthetic Benchmark: Can Frontier Models Judge Beauty?
Yichen Feng, Yuetai Li, Chunjiang Liu +14
Multimodal large language models (MLLMs) are now routinely deployed for visual understanding, generation, and curation. A substantial fraction of these applications require an expl…
SkillGen: Verified Inference-Time Agent Skill Synthesis
Yuchen Ma, Yue Huang, Han Bao +5
Skills are a promising way to improve LLM agent capabilities without retraining, while keeping the added procedure reusable and controllable. However, high-quality skills are still…
NARRA-Gym for Evaluating Interactive Narrative Agents
Yue Huang, Yuchen Ma, Jiayi Ye +14
Interactive narrative tasks require LLMs to sustain a coherent, evolving story while adapting to a user over multiple turns. However, suitable benchmarks for this setting are limit…
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…
Dual Optimal: Make Your LLM Peer-like with Dignity
Xiangqi Wang, Yue Huang, Haomin Zhuang +2
Current aligned language models exhibit a dual failure mode we term the Evasive Servant: they sycophantically validate flawed user beliefs while deflecting responsibility with boil…
Alignment Risks from Capability-Seeking RL Training
Yujun Zhou, Yue Huang, Han Bao +8
While most AI alignment research focuses on preventing models from generating explicitly harmful content, a more subtle risk arises from capability-seeking RL training in vulnerabl…
The Role of Computing Resources in Publishing Foundation Model Research
Yuexing Hao, Yue Huang, Haoran Zhang +8
Cutting-edge research in Artificial Intelligence (AI) requires considerable resources, including Graphics Processing Units (GPUs), data, and human resources. In this paper, we eval…
Building a Foundational Guardrail for General Agentic Systems via Synthetic Data
Yue Huang, Hang Hua, Yujun Zhou +11
While LLM agents can plan multi-step tasks, intervening at the planning stage-before any action is executed-is often the safest way to prevent harm, since certain risks can lead to…
Exploring Multi-Temperature Strategies for Token- and Rollout-Level Control in RLVR
Haomin Zhuang, Yujun Zhou, Taicheng Guo +4
Reinforcement Learning has demonstrated substantial improvements in the reasoning abilities of Large Language Models (LLMs), exhibiting significant applicability across various dom…