1 citations · 2 across the 9 of their papers we have counts for
10 papers
X-Tree: Tokenizing Reusable Experience for Efficient Agent Generalization
Sitao Cheng, Xunjian Yin, Zhiyuan Sun +4
Multi-step agents are trained on flat action streams: SFT and RLVR weight every token uniformly and ignore the sub-procedures that recur across tasks, the hierarchy that lets human…
MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs
Junwei Liao, Haoting Shi, Ruiwen Zhou +9
Episodic memory allows LLM agents to accumulate and retrieve experience, but current methods treat each memory independently, i.e., evaluating retrieval quality in isolation withou…
MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
Shengtao Zhang, Jiaqian Wang, Ruiwen Zhou +11
The hallmark of human intelligence is the self-evolving ability to master new skills by learning from past experiences. However, current AI agents struggle to emulate this self-evo…
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…
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…
LLMs Can't Handle Peer Pressure: Crumbling under Multi-Agent Social Interactions
Maojia Song, Tej Deep Pala, Ruiwen Zhou +5
Large language models (LLMs) are increasingly integrated into multi-agent systems (MAS), where peer interactions shape individual decisions. While prior work has mainly examined co…
AntiLeakBench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge
Xiaobao Wu, Liangming Pan, Yuxi Xie +7
Data contamination hinders fair LLM evaluation by introducing test data into newer models' training sets. Existing studies solve this challenge by updating benchmarks with newly co…
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…
TRAD: Enhancing LLM Agents with Step-Wise Thought Retrieval and Aligned Decision
Ruiwen Zhou, Yingxuan Yang, Muning Wen +6
Numerous large language model (LLM) agents have been built for different tasks like web navigation and online shopping due to LLM's wide knowledge and text-understanding ability. A…
Is Risk-Sensitive Reinforcement Learning Properly Resolved?
Ruiwen Zhou, Minghuan Liu, Kan Ren +3
Due to the nature of risk management in learning applicable policies, risk-sensitive reinforcement learning (RSRL) has been realized as an important direction. RSRL is usually achi…