collaborators

8 papers

cs.AI2026

The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows

Junbo Li, Boyi Liu, Canwen Xu +5

Recent systems for optimizing prompts, programs, and ML workflows typically rely on explicit outer-loop controllers such as evolutionary search, bandits, or textual-gradient method…

cs.LG2026

Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning

Peihao Wang, Shan Yang, Xijun Wang +8

Associative memory has long underpinned the design of sequential models. Beyond recall, humans reason by projecting future states and selecting goal-directed actions, a capability…

cs.AI2026

Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems

Jianing Zhu, Yeonju Ro, John Robertson +5

Long-lived AI agents are increasingly deployed as persistent operational systems, yet they are still evaluated like freshly initialized models. Day-one benchmarks miss a basic syst…

cs.LG2026

Improving the Throughput of Diffusion-based Large Language Models via a Training-Free Confidence-Aware Calibration

Jucheng Shen, Gaurav Sarkar, Yeonju Ro +4

We present CadLLM, a training-free method to accelerate the inference throughput of diffusion-based LLMs (dLLMs). We first investigate the dynamic nature of token unmasking confide…

cs.AI2026

MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games

Yunfei Xie, Kevin Wang, Bobby Cheng +9

Multi-turn, multi-agent LLM game evaluations often exhibit substantial run-to-run variance. In long-horizon interactions, small early deviations compound across turns and are ampli…

cs.MA2025

Sherlock: Reliable and Efficient Agentic Workflow Execution

Yeonju Ro, Haoran Qiu, Íñigo Goiri +6

With the increasing adoption of large language models (LLM), agentic workflows, which compose multiple LLM calls with tools, retrieval, and reasoning steps, are increasingly replac…