collaborators

12 papers

cs.LG2026

ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs

Wonjun Kang, Kevin Galim, Seunghyuk Oh +8

While most autoregressive LLMs are constrained to one-by-one decoding, diffusion LLMs (dLLMs) have attracted growing interest for their potential to dramatically accelerate inferen…

cs.LG2026

Rollout Pass-Rate Control: Steering Binary-Reward RL Toward Its Most Informative Regime

Tianshu Zhu, Wenyu Zhang, Xiaoying Zuo +8

Agentic reinforcement learning (RL) for software engineering spends much of its compute on stateful trajectories whose grouped binary rewards are highly skewed and weakly contrasti…

cs.AI2026

AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning

Haotian Zhao, Songlin Zhou, Yuxin Zhang +9

Reinforcement learning (RL) has substantially improved the ability of large language model (LLM) agents to interact with environments and solve multi-turn tasks. However, effective…

cs.AI2026

MEMENTO: Teaching LLMs to Manage Their Own Context

Vasilis Kontonis, Yuchen Zeng, Shivam Garg +7

Reasoning models think in long, unstructured streams with no mechanism for compressing or organizing their own intermediate state. We introduce MEMENTO: a method that teaches model…

cs.LG2026

Demonstrations, CoT, and Prompting: A Theoretical Analysis of ICL

Xuhan Tong, Yuchen Zeng, Jiawei Zhang

In-Context Learning (ICL) enables pretrained LLMs to adapt to downstream tasks by conditioning on a small set of input-output demonstrations, without any parameter updates. Althoug…

cs.AI2026

SWE-Hub: A Unified Production System for Scalable, Executable Software Engineering Tasks

Yucheng Zeng, Shupeng Li, Daxiang Dong +11

Progress in software-engineering agents is increasingly constrained by the scarcity of executable, scalable, and realistic data for training and evaluation. This scarcity stems fro…