XUANMING ZHANG

XUANMINGZHANG

·

https://xmzhangai.github.io/

AI & ML interests

Code Generation；Social Agent；Algorithm Engineering

Recent Activity

authored a paper 26 days ago

Human Decision-making is Susceptible to AI-driven Manipulation

authored a paper 26 days ago

SocialEval: Evaluating Social Intelligence of Large Language Models

authored a paper 26 days ago

JumpStarter: Human-AI Planning with Task-Structured Context Curation

View all activity

Organizations

upvoted a paper 28 days ago

Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding

Paper • 2606.21906 • Published Jun 20 • 25

upvoted a paper 9 months ago

Generalization or Memorization: Dynamic Decoding for Mode Steering

Paper • 2510.22099 • Published Oct 25, 2025 • 4

upvoted a paper 10 months ago

ReST-RL: Achieving Accurate Code Reasoning of LLMs with Optimized Self-Training and Decoding

Paper • 2508.19576 • Published Aug 27, 2025 • 2

upvoted 3 papers about 1 year ago

Agent-SafetyBench: Evaluating the Safety of LLM Agents

Paper • 2412.14470 • Published Dec 19, 2024 • 12

MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems

Paper • 2505.18943 • Published May 25, 2025 • 25

Seeker: Towards Exception Safety Code Generation with Intermediate Language Agents Framework

Paper • 2412.11713 • Published Dec 16, 2024 • 6

upvoted a paper almost 2 years ago

Seeker: Enhancing Exception Handling in Code with LLM-based Multi-Agent Approach

Paper • 2410.06949 • Published Oct 9, 2024 • 6