43 citations · 56 across the 17 of their papers we have counts for
21 papers
TokenEconomizer: Experience-Driven Black-Box Cost Control for Coding Agents
Aaron J. Li, Weijia Xu, Chandan Singh +8
Advances in frontier coding agents have sharply increased the token costs of AI-assisted software engineering. Their token efficiency is typically evaluated on isolated tasks, wher…
Learning User Representations to Improve Simulation Fidelity
Shuhaib Mehri, Philippe Laban, Michel Galley +3
User simulators enable interactive training and evaluation of AI assistants at scale. Yet current simulators struggle to reproduce the diverse behaviors of real users, leading to a…
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…
Reward Hacking Challenges Oversight of Autonomous Research Agents
Yue Huang, Zhangchen Xu, Yuchen Ma +12
Autonomous research agents can design experiments, evaluate results, and write reports, giving them control over both a scientific result and the evidence used to support it. This…
StudentSim: Training LLM-based Student Simulators
Ke Yang, Chenglong Wang, Michel Galley +4
AI tutors are most useful when they adapt to each student's strengths, weaknesses, and preferred guidance, but evidence about which guidance works for which student is sparse, slow…
VGI-Bench: Probing Visual Intelligence in Video Generation Models
Xuan He, Cong Wei, Yuhao Cheng +20
Recent studies suggest that video generation models can exhibit certain forms of zero-shot visual reasoning through generated frames. Yet reliable evaluation remains challenging: b…
Do Proactive Agents Need an LLM to Decide When to Act?
Xiaoze Liu, Ruowang Zhang, Amir H. Abdi +5
Proactive assistants continuously decide when to intervene and what context should support the intervention. Large language model (LLM) pipelines repeatedly interpret activity hist…
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…
Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviors
Shuhaib Mehri, Philippe Laban, Sumuk Shashidhar +4
As user simulators are increasingly used for interactive training and evaluation of AI assistants, it is essential that they represent the diverse behaviors of real users. While ex…
Agentic-imodels: Evolving agentic interpretability tools via autoresearch
Chandan Singh, Yan Shuo Tan, Weijia Xu +4
Agentic data science (ADS) systems are rapidly improving their capability to autonomously analyze, fit, and interpret data, potentially moving towards a future where agents conduct…
Test-Time Learning with an Evolving Library
Weijia Xu, Alessandro Sordoni, Chandan Singh +4
We introduce EvoLib, a test-time learning framework that enables large language models to accumulate, reuse, and evolve knowledge across problem instances without parameter updates…
PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents
Ke Yang, Zixi Chen, Xuan He +6
Long-term memory is essential for large language model (LLM) agents operating in complex environments, yet existing memory designs are either task-specific and non-transferable, or…
Dyna-Mind: Learning to Simulate from Experience for Better AI Agents
Xiao Yu, Baolin Peng, Michel Galley +6
Reasoning models have recently shown remarkable progress in domains such as math and coding. However, their expert-level abilities in math and coding contrast sharply with their pe…
SimulatorArena: Are User Simulators Reliable Proxies for Multi-Turn Evaluation of AI Assistants?
Yao Dou, Michel Galley, Baolin Peng +6
Large language models (LLMs) are increasingly used in interactive applications, and human evaluation remains the gold standard for assessing their performance in multi-turn convers…
Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents
Xiao Yu, Baolin Peng, Ruize Xu +5
Recent progress in reasoning with large language models (LLMs), such as DeepSeek-R1, demonstrates impressive capabilities in domains like mathematics and coding, by exhibiting comp…
CollabLLM: From Passive Responders to Active Collaborators
Shirley Wu, Michel Galley, Baolin Peng +7
Large Language Models are typically trained with next-turn rewards, limiting their ability to optimize for long-term interaction. As a result, they often respond passively to ambig…
Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities
Chung-En Sun, Xiaodong Liu, Weiwei Yang +5
Recent research has shown that Large Language Models (LLMs) are vulnerable to automated jailbreak attacks, where adversarial suffixes crafted by algorithms appended to harmful quer…
ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning
Xiao Yu, Baolin Peng, Vineeth Vajipey +4
Autonomous agents have demonstrated significant potential in automating complex multistep decision-making tasks. However, even state-of-the-art vision-language models (VLMs), such…
Rethinking Interpretability in the Era of Large Language Models
Chandan Singh, Jeevana Priya Inala, Michel Galley +2
Interpretable machine learning has exploded as an area of interest over the last decade, sparked by the rise of increasingly large datasets and deep neural networks. Simultaneously…
Teaching Language Models to Self-Improve through Interactive Demonstrations
Xiao Yu, Baolin Peng, Michel Galley +2
The self-improving ability of large language models (LLMs), enabled by prompting them to analyze and revise their own outputs, has garnered significant interest in recent research.…
MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
Pan Lu, Hritik Bansal, Tony Xia +7
Large Language Models (LLMs) and Large Multimodal Models (LMMs) exhibit impressive problem-solving skills in many tasks and domains, but their ability in mathematical reasoning in…