Author

Yuan-Fang Li

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

Learning from Viable Failure Prefixes: Milestone Viability Potential Policy Optimization for Long-Horizon LLM Agents

Long-horizon LLM agents require reinforcement learning methods that can assign credit to intermediate decisions under sparse and delayed rewards. Existing group-based methods such as GRPO and GiGPO alleviate this issue by comparing rollout returns or repeated anchor states, but they still fail when the compared returns...

Qi Zhou, Yuan-Fang Li · 0 citations

#artificial intelligence Preprint Aug 2026

MemFuse: Multi-Source Memory Fusion from Fragmented Observations

Experiments on MemFuseBench show that MemFuse achieves the best overall performance among the evaluated memory systems under all three LLM settings and consistently improves performance on questions requiring cross-source evidence fusion.

Chao Li, Yuan-Fang Li, Wenhao Wu et al. · 0 citations