Author

Tian-Jun Yao

3 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.

Preprint Oct 2026

CoMem: Learning to Anticipate Failures from Retrieved Experience

Reflection lets LLM agents improve from their own attempts, but the memory it builds is local to a single task, so an agent reflecting on its own tends to revisit the same explanation for failure. Cross-task reflective memory addresses this in two forms: retrieved memory keeps past experience explicit and looks up rela...

Yu-Liang Shen, Ming Shen, Tian-Jun Yao · 0 citations

Preprint Oct 2026

Not All Test-Time Compute Is Evidence: Model-Specific Bias in LLM Reasoning

Test-time scaling methods implicitly assume that additional computation from the same model provides independent evidence. We show that this assumption fails within a single reasoning model: errors are correlated across repeated samples, across reasoning depth, and in the model's own self-evaluation, so more compute fr...

Ming Shen, Tian-Jun Yao · 0 citations

#machine learning Preprint Oct 2026

Response-Informed Value Estimation for Cost-Aware Multi-Turn LLM Routing

RIVET jointly trains two value estimators over a shared state-model representation: a deployable Routing Value Estimator that scores candidate models from pre-call information, and a training-only Response-Informed Value Estimator that additionally observes the realized response.

Hao-Tian Yan, Jia-Qi Liu, Bing-Yi Jing et al. · 0 citations