activity
20242026
collaborators

6 papers

cs.CL2026

S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?

Jiajun Shi, Siyuan Tao, Yuhao Wu +18

Large language models (LLMs) increasingly interact with external environments and accumulate substantial behavioral experience, yet existing agent benchmarks largely evaluate them…

cs.SE2026

Understanding by Reconstruction: Reversing the Software Development Process for LLM Pretraining

Zhiyuan Zeng, Yichi Zhang, Yong Shan +11

While Large Language Models (LLMs) have achieved remarkable success in code generation, they often struggle with the deep, long-horizon reasoning required for complex software engi…

cs.CL2025

KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation

Jiajun Shi, Jian Yang, Jiaheng Liu +26

Recent advancements in large language models (LLMs) underscore the need for more comprehensive evaluation methods to accurately assess their reasoning capabilities. Existing benchm…

cs.CL2025

MoL for LLMs: Dual-Loss Optimization to Enhance Domain Expertise While Preserving General Capabilities

Jingxue Chen, Qingkun Tang, Qianchun Lu +1

Although large language models (LLMs) perform well in general tasks, domain-specific applications suffer from hallucinations and accuracy limitations. Continual Pre-Training (CPT)…

cs.CL2024

KARPA: A Training-free Method of Adapting Knowledge Graph as References for Large Language Model's Reasoning Path Aggregation

Siyuan Fang, Kaijing Ma, Tianyu Zheng +4

Large language models (LLMs) demonstrate exceptional performance across a variety of tasks, yet they are often affected by hallucinations and the timeliness of knowledge. Leveragin…

cs.LG2024

Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition

Zi-Hao Zhou, Siyuan Fang, Zi-Jing Zhou +3

Long-tailed semi-supervised learning poses a significant challenge in training models with limited labeled data exhibiting a long-tailed label distribution. Current state-of-the-ar…