Zhuosheng Zhang

DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning

Agent-ScanKit: Unraveling Memory and Reasoning of Multimodal Agents via Sensitivity Perturbations

First Things First: Teaching LLM-Based Agents to Prioritize Must-Haves before Nice-to-Haves

When Disagreements Elicit Robustness: Investigating Self-Repair Capabilities under LLM Multi-Agent Disagreements

Chain-of-Trigger: An Agentic Backdoor that Paradoxically Enhances Agentic Robustness

DRQA: Dynamic Reasoning Quota Allocation for Controlling Overthinking in Reasoning Large Language Models

DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning

Say One Thing, Do Another? Diagnosing Reasoning-Execution Gaps in VLM-Powered Mobile-Use Agents

Disagreements in Reasoning: How a Model's Thinking Process Dictates Persuasion in Multi-Agent Systems

The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systems

XBOUND: Exploring Capability Boundaries of Device-Control Agents at the State Level

Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding

Thoughts Are All Over the Place: On the Underthinking of Long Reasoning Models

RaSA: Rank-Sharing Low-Rank Adaptation

Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models

Probing then Editing Response Personality of Large Language Models

ChemAgent: Self-updating Memories in Large Language Models Improves Chemical Reasoning

Do NOT Think That Much for 2+3=? On the Overthinking of Long Reasoning Models

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models