AI.info

Wenjie Li

Explore Wenjie Li on AI.info.

• LigBench: A Unified and Human-Aligned Benchmark for LLM-based Research Idea Generation
• AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts
• To Retrieve or To Think? Cross-Boundary Context Evolution for Multi-hop Complex Reasoning
• Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models
• Ophiuchus: Incentivizing Tool-augmented "Think with Images" for Joint Medical Segmentation, Understanding and Reasoning
• SCALE: Selective Resource Allocation for Overcoming Performance Bottlenecks in Mathematical Test-time Scaling
• Merlin's Whisper: Enabling Efficient Reasoning in Large Language Models via Black-box Persuasive Prompting
• Parallel Test-Time Scaling for Latent Reasoning Models