papers

Publications (11)

cs.AI2026

How Hard Does It Think? Analyzing Step-Aware Reasoning Energy in LLM Chain-of-Thought Trajectories

Hui Wei, Junda Wu, Sheldon Yu +8

Understanding how computational effort is allocated across individual chain-of-thought (CoT) reasoning steps remains an open challenge: existing interpretability methods rely on ou…

cs.LG2026

CTRLS: Chain-of-Thought Reasoning via Latent State-Transition

Junda Wu, Yuxin Xiong, Xintong Li +7

Chain-of-thought (CoT) reasoning enables large language models (LLMs) to break down complex problems into interpretable intermediate steps, significantly enhancing model transparen…

cs.AI2026

Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering

Sheldon Yu, Tong Yu, Xunyi Jiang +6

Extended reasoning has become standard for frontier Large Language Models (LLMs), yet the trajectories these models produce remain largely uncontrollable. Existing methods for shap…

cs.CL2026

Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainability

Sizhe Zhou, Sheldon Yu, Hui Wei +8

The paper systematically investigates how large language model agents can use a filesystem of markdown files as long‑term memory, examining different organization strategies, tools…

#llm agents#filesystem memory#memory organization#retrieval efficiency
cs.LG2026

RRPO: Reference-Relative Policy Optimization with Stratified Conditional Rollouts

Yuxin Xiong, Xunyi Jiang, Rohan Surana +8

Group Relative Policy Optimization (GRPO) has shown strong effectiveness in reinforcement learning from verifiable feedback, where sampled rollouts can be compared within a group u…

cs.AI2026

OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agents

Sheldon Yu, Junda Wu, Xintong Li +6

Large language model agents interleave reasoning, action selection, and observation to solve sequential decision-making tasks. In deployed settings where agents repeatedly handle r…

cs.LG2026

WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning

Gagan Mundada, Zihan Huang, Rohan Surana +8

Group Relative Policy Optimization (GRPO) is effective for training language models on complex reasoning. However, since the objective is defined relative to a group of sampled tra…

cs.AI2026

A Low-Latency Fraud Detection Layer for Detecting Adversarial Interaction Patterns in LLM-Powered Agents

Sheldon Yu, Yingcheng Sun, Hanqing Guo +1

Large Language Model (LLM)-powered agents demonstrate strong capabilities in autonomous task execution, tool use, and multi-step reasoning. However, their increasing autonomy also…

cs.LG2026

MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization

Rohan Surana, Xintong Li, Sheldon Yu +7

Multi-negative preference optimization under the Plackett--Luce (PL) model extends Direct Preference Optimization (DPO) by leveraging comparative signals across one preferred and m…

cs.LG2026

Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning

Rohan Surana, Gagan Mundada, Xunyi Jiang +19

Reinforcement learning (RL) has become a central post-training tool for improving the reasoning abilities of large language models (LLMs). In these systems, the rollout, the trajec…

cs.CL2026

Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics

Sheldon Yu, Yuxin Xiong, Junda Wu +6

Recent advances in chain-of-thought (CoT) prompting have enabled large language models (LLMs) to perform multi-step reasoning. However, the explainability of such reasoning remains…