activity
20242026
collaborators

19 papers

cs.SE2026

ConcernBERT: Learning Responsibilities Using Class Membership

J. Lefever, J. Xu, Y. Cai +2

The principles of separation of concerns, high cohesion, and single responsibility are among the most well-known in software design. However, their application often remains philos…

cs.CL2026

Stabilizing Efficient Reasoning with Step-Level Advantage Selection

Han Wang, Xiaodong Yu, Jialian Wu +4

Large language models (LLMs) achieve strong reasoning performance by allocating substantial computation at inference time, often generating long and verbose reasoning traces. While…

cs.AI2026

DeepCompress: A Dual Reward Strategy for Dynamically Exploring and Compressing Reasoning Chains

Tian Liang, Wenxiang Jiao, Zhiwei He +3

Large Reasoning Models (LRMs) have demonstrated impressive capabilities but suffer from cognitive inefficiencies like "overthinking" simple problems and "underthinking" complex one…

cs.AI2026

Free(): Learning to Forget in Malloc-Only Reasoning Models

Yilun Zheng, Dongyang Ma, Tian Liang +5

Reasoning models enhance problem-solving by scaling test-time compute, yet they face a critical paradox: excessive thinking tokens often degrade performance rather than improve it.…

cs.AI2025

SciAgent: A Unified Multi-Agent System for Generalistic Scientific Reasoning

Xuchen Li, Ruitao Wu, Xuanbo Liu +17

Recent advances in large language models have enabled AI systems to achieve expert-level performance on domain-specific scientific tasks, yet these systems remain narrow and handcr…

cs.CL2025

The End of Manual Decoding: Towards Truly End-to-End Language Models

Zhichao Wang, Dongyang Ma, Xinting Huang +6

The "end-to-end" label for LLMs is a misnomer. In practice, they depend on a non-differentiable decoding process that requires laborious, hand-tuning of hyperparameters like temper…