16 citations · 31 across the 34 of their papers we have counts for
37 papers
CAST: Critique-Aware Supervision for Training Reliable Long-Horizon Tool-Calling Agents
Amir Saeidi, Zehua Zhang, Rishitosh Singh +6
Large language model (LLM) agents are increasingly deployed in long-horizon, interactive, and stateful environments. In these settings, a single wrong action, such as refunding the…
DynamicMem: A Long-Horizon Memory Benchmark in Real-World Settings
Wenya Xie, Shengming Zhou, Zelin Li +9
LLM agents increasingly act as personal assistants that must remember a user's profile over months: who they are (attributes), what they routinely do (habits), and what they prefer…
FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments
Amir Saeidi, Venkatesh Mishra, Souradeep Mukhopadhyay +4
Large Language Models are being increasingly deployed as the decision-making core of autonomous agents capable of effecting change in external environments. Yet, in conversational…
Scaling Teams or Scaling Time? Memory Enabled Lifelong Learning in LLM Multi-Agent Systems
Shanglin Wu, Yuyang Luo, Yueqing Liang +4
Large language model (LLM) multi-agent systems can scale along two distinct dimensions: by increasing the number of agents and by improving through accumulated experience over time…
A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents
Wei-Chieh Huang, Weizhi Zhang, Yueqing Liang +56
Research in artificial intelligence is shifting from model innovations and benchmark scores towards problem definition and rigorous real-world evaluation. As the field enters the "…
Rep2Text: Decoding Full Text from a Single LLM Token Representation
Haiyan Zhao, Zirui He, Yiming Tang +4
Large language models represent text as hidden numerical patterns, but what information these representations actually contain remains a mystery. Can we recover the original text f…
Towards Strong Certified Defense with Universal Asymmetric Randomization
Hanbin Hong, Ashish Kundu, Ali Payani +2
Randomized smoothing has become essential for achieving certified adversarial robustness in machine learning models. However, current methods primarily use isotropic noise distribu…
Learning Bug Context for PyTorch-to-JAX Translation with LLMs
Hung Phan, Son Vu, Tuan Dinh +3
Large language models (LLMs) have shown strong performance on code translation between widely used programming languages. However, translation becomes much less reliable for domain…
LogitTrace: Detecting Benchmark Contamination via Layerwise Logit Trajectories
Zirui He, Haiyan Zhao, Yingcong Li +2
Large language models (LLMs) are commonly evaluated on challenging benchmarks such as AIME and Math500, where benchmark contamination can make memorized solutions appear as genuine…
How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on -bench
Venkatesh Mishra, Amir Saeidi, Satyam Raj +5
Recent advances in reasoning and planning capabilities of large language models (LLMs) have enabled their potential as autonomous agents capable of tool use in dynamic environments…
Effective Training Data Synthesis for Improving MLLM Chart Understanding
Yuwei Yang, Zeyu Zhang, Yunzhong Hou +5
Being able to effectively read scientific plots, or chart understanding, is a central part toward building effective agents for science. However, existing multimodal large language…
Command-V: Pasting LLM Behaviors via Activation Profiles
Barry Wang, Avi Schwarzschild, Alexander Robey +4
Retrofitting large language models (LLMs) with new behaviors typically requires full finetuning or distillation-costly steps that must be repeated for every architecture. In this w…
AutoSDT: Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists
Yifei Li, Hanane Nour Moussa, Ziru Chen +16
Despite long-standing efforts in accelerating scientific discovery with AI, building AI co-scientists remains challenging due to limited high-quality data for training and evaluati…
Model Editing as a Double-Edged Sword: Steering Agent Ethical Behavior Toward Beneficence or Harm
Baixiang Huang, Zhen Tan, Haoran Wang +6
Agents based on Large Language Models (LLMs) have demonstrated strong capabilities across a wide range of tasks. However, deploying LLM-based agents in high-stakes domains comes wi…
AALC: Large Language Model Efficient Reasoning via Adaptive Accuracy-Length Control
Ruosen Li, Ziming Luo, Quan Zhang +4
Large reasoning models (LRMs) achieve impressive reasoning capabilities by generating lengthy chain-of-thoughts, but this "overthinking" incurs high latency and cost without commen…
SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models
Zirui He, Mingyu Jin, Bo Shen +3
Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but controlling their behavior reliably remains challenging…
Personalized Federated Fine-tuning for Heterogeneous Data: An Automatic Rank Learning Approach via Two-Level LoRA
Jie Hao, Yuman Wu, Ali Payani +2
We study the task of personalized federated fine-tuning with heterogeneous data in the context of language models, where clients collaboratively fine-tune a language model (e.g., B…
SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models
Zirui He, Haiyan Zhao, Yiran Qiao +4
The ability of large language models (LLMs) to follow instructions is crucial for their practical applications, yet the underlying mechanisms remain poorly understood. This paper p…
Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning
Venkatesh Mishra, Bimsara Pathiraja, Mihir Parmar +5
Reasoning abilities of LLMs have been a key focus in recent years. One challenging reasoning domain with interesting nuances is legal reasoning, which requires careful application…
Benchmarking LLMs for Political Science: A United Nations Perspective
Yueqing Liang, Liangwei Yang, Chen Wang +6
Large Language Models (LLMs) have achieved significant advances in natural language processing, yet their potential for high-stake political decision-making remains largely unexplo…
ProFL: Performative Robust Optimal Federated Learning
Xue Zheng, Tian Xie, Xuwei Tan +2
Performative prediction is a framework that captures distribution shifts that occur during the training of machine learning models due to their deployment. As the trained model is…
Can Knowledge Editing Really Correct Hallucinations?
Baixiang Huang, Canyu Chen, Xiongxiao Xu +2
Large Language Models (LLMs) suffer from hallucinations, referring to the non-factual information in generated content, despite their superior capacities across tasks. Meanwhile, k…
Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution
Haiyan Zhao, Heng Zhao, Bo Shen +3
Probing learned concepts in large language models (LLMs) is crucial for understanding how semantic knowledge is encoded internally. Training linear classifiers on probing tasks is…
LightPure: Realtime Adversarial Image Purification for Mobile Devices Using Diffusion Models
Hossein Khalili, Seongbin Park, Vincent Li +4
Autonomous mobile systems increasingly rely on deep neural networks for perception and decision-making. While effective, these systems are vulnerable to adversarial machine learnin…