activity
20242026
collaborators

7 papers

cs.AI2026

Atomic Skills are the Prerequisite: When Reinforcement Learning Synthesizes Compositional Reasoning, and When It Only Amplifies

Sitao Cheng, Xunjian Yin, Ruiwen Zhou +5

Does Reinforcement Learning (RL) merely amplify existing skills, or synthesize novel skills? We investigate this question through the lens of Complementary Reasoning: the critical…

cs.CL2026

LEDOM: Reverse Language Model

Xunjian Yin, Sitao Cheng, Yuxi Xie +6

Autoregressive language models are trained exclusively left-to-right. We explore the complementary factorization, training right-to-left at scale, and ask what reasoning patterns e…

cs.AI2025

Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement

Xunjian Yin, Xinyi Wang, Liangming Pan +3

The rapid advancement of large language models (LLMs) has significantly enhanced the capabilities of AI-driven agents across various tasks. However, existing agentic systems, wheth…

cs.LG2025

InductionBench: LLMs Fail in the Simplest Complexity Class

Wenyue Hua, Tyler Wong, Sun Fei +3

Large language models (LLMs) have shown remarkable improvements in reasoning and many existing benchmarks have been addressed by models such as o1 and o3 either fully or partially.…

cs.LG2024

Investigating the Transferability of Code Repair for Low-Resource Programming Languages

Kyle Wong, Alfonso Amayuelas, Liangming Pan +1

Large language models (LLMs) have shown remarkable performance on code generation tasks. A recent use case is iterative code repair, where an LLM fixes an incorrect program by rati…

cs.CL2024

Understanding the Interplay between Parametric and Contextual Knowledge for Large Language Models

Sitao Cheng, Liangming Pan, Xunjian Yin +2

Large language models (LLMs) encode vast amounts of knowledge during pre-training (parametric knowledge, or PK) and can further be enhanced by incorporating contextual knowledge (C…