AI.info

Xiangliang Zhang

Explore Xiangliang Zhang on AI.info.

• GTA: Graph Theory Agent and Benchmark for Algorithmic Graph Reasoning with LLMs
• RankLLM: Weighted Ranking of LLMs by Quantifying Question Difficulty
• Alignment Risks from Capability-Seeking RL Training
• Evaluating Large Language Models in Scientific Discovery
• SPA: Achieving Consensus in LLM Alignment via Self-Priority Optimization
• MTSQL-R1: Towards Long-Horizon Multi-Turn Text-to-SQL via Agentic Training