papers

Publications (12)

cs.AI2026

Unifying and Optimizing Data Values for Selection via Sequential Decision-Making

Hongliang Chi, Qiong Wu, Zhengyi Zhou +3

Data selection has emerged as a crucial downstream application of data valuation, yet the theoretical foundations for using data values in selection remain underexplored. We reform…

cs.LG2025

On the Effect of Sampling Diversity in Scaling LLM Inference

Tianchun Wang, Zichuan Liu, Yuanzhou Chen +5

Large language model (LLM) scaling inference is key to unlocking greater performance, and leveraging diversity has proven an effective way to enhance it. Motivated by the observed…

cs.CV2025

Simple Agents Outperform Experts in Biomedical Imaging Workflow Optimization

Xuefei, Wang, Kai A. Horstmann +9

Adapting production-level computer vision tools to bespoke scientific datasets is a critical "last mile" bottleneck. Current solutions are impractical: fine-tuning requires large a…

cs.LG2025

Optimal Pricing for Data-Augmented AutoML Marketplaces

Minbiao Han, Jonathan Light, Steven Xia +3

Organizations often lack sufficient data to effectively train machine learning (ML) models, while others possess valuable data that remains underutilized. Data markets promise to u…

cs.SE2025

Scattered Forest Search: Smarter Code Space Exploration with LLMs

Jonathan Light, Yue Wu, Yiyou Sun +6

We frame code generation as a black-box optimization problem within the code space and demonstrate how optimization-inspired techniques can enhance inference scaling. Based on this…

cs.AI2024

PIANIST: Learning Partially Observable World Models with LLMs for Multi-Agent Decision Making

Jonathan Light, Sixue Xing, Yuanzhe Liu +7

Effective extraction of the world knowledge in LLMs for complex decision-making tasks remains a challenge. We propose a framework PIANIST for decomposing the world model into seven…

cs.LG2025

DISC: Dynamic Decomposition Improves LLM Inference Scaling

Jonathan Light, Wei Cheng, Benjamin Riviere +6

Inference scaling methods for LLMs often rely on decomposing problems into steps (or groups of tokens), followed by sampling and selecting the best next steps. However, these steps…

cs.AI2023

AvalonBench: Evaluating LLMs Playing the Game of Avalon

Jonathan Light, Min Cai, Sheng Shen +1

In this paper, we explore the potential of Large Language Models (LLMs) Agents in playing the strategic social deduction game, Resistance Avalon. Players in Avalon are challenged n…

cs.LG2026

Actor-Curator: Co-adaptive Curriculum Learning via Policy-Improvement Bandits for RL Post-Training

Zhengyao Gu, Jonathan Light, Raul Astudillo +7

Post-training large foundation models with reinforcement learning typically relies on massive and heterogeneous datasets, making effective curriculum learning both critical and cha…

cs.AI2025

Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search

Jonathan Light, Min Cai, Weiqin Chen +5

Traditional reinforcement learning and planning typically requires vast amounts of data and training to develop effective policies. In contrast, large language models (LLMs) exhibi…

cs.LG2025

TDRM: Smooth Reward Models with Temporal Difference for LLM RL and Inference

Dan Zhang, Min Cai, Jonathan Light +3

Reward models are central to both reinforcement learning (RL) with language models and inference-time verification. However, existing reward models often lack temporal consistency,…

cs.LG2025

Dataset Distillation for Offline Reinforcement Learning

Jonathan Light, Yuanzhe Liu, Ziniu Hu

Offline reinforcement learning often requires a quality dataset that we can train a policy on. However, in many situations, it is not possible to get such a dataset, nor is it easy…