Skip to main content
Search

Ruimin Pei

2 related articles

Subscribe to updates
  1. arXiv

    LLM agents learn environment facts and execution tips on separate tracks: TTSE beats a unified rule bank by about 3 points across five SOPBench domains

    Huawei's Poisson Lab introduces TTSE, which splits what an LLM agent learns from interaction into two independently evolving tracks: facts about what the environment is like, and procedures for what to do under which condition. Prior self-evolution work treated environmental knowledge as fixed external input or optimized skills alone. Across 892 tasks in five SOPBench domains and three repeats, the dual-track version scored 2.99 percentage points above a unified single-track bank, with a 95% confidence interval of 2.34 to 3.65 points.

  2. arXiv

    FPSRG turns personality profiles into a searchable catalog: five-level vectors plus prompts cover 98.7% of 25–75 targets

    FPSRG replaces training one adapter per profile with shared first-person post-training plus a small set of retrievable directions. With the model frozen, it measures complete multidimensional scores for coefficient combinations and stores them in a catalog searched by target scores. In the five-dimensional non-thinking instance, the five-level vector catalog covers 92.2% of fixed targets in the 25–75 region, rising to 98.7% when combined with the prompt catalog.

You’re all caught up