7 papers
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…
Differentiable Evolutionary Reinforcement Learning
Sitao Cheng, Tianle Li, Xuhan Huang +2
Crafting effective reward signals remains a central challenge in Reinforcement Learning (RL), especially for complex reasoning tasks. Existing automated reward optimization methods…
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…
Epistemic Context Learning: Building Trust the Right Way in LLM-Based Multi-Agent Systems
Ruiwen Zhou, Maojia Song, Xiaobao Wu +8
Individual agents in multi-agent (MA) systems often lack robustness, tending to blindly conform to misleading peers. We show this weakness stems from both sycophancy and inadequate…
Dynamic Evaluation for Oversensitivity in LLMs
Sophia Xiao Pu, Sitao Cheng, Xin Eric Wang +1
Oversensitivity occurs when language models defensively reject prompts that are actually benign. This behavior not only disrupts user interactions but also obscures the boundary be…
RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios
Ruiwen Zhou, Wenyue Hua, Liangming Pan +4
This paper introduces RuleArena, a novel and challenging benchmark designed to evaluate the ability of large language models (LLMs) to follow complex, real-world rules in reasoning…