Jiafei Wu

PertMind: Eliciting Emergent Biological Reasoning in LLM via Reinforcement Learning on Cellular Perturbation Data

It is shown that cellular perturbation atlases can instead become reinforcement-learning environments, where measured gene responses provide computable rewards for biological reasoning, and introduces PertMind, which combines trusted-trajectory supervised initialization with gene-, pathway-, and format-level reinforcem...

Beyond Outcome Gaps: Process-Aware Fairness Diagnosis for LLM-based Multi-Agent Decision Systems

SCOPED-Hiring reveals that balanced final hire rates can mask hidden trajectory unfairness in multi-agent decision trajectories and reduces total layered burden by 72.3% while shifting the hire rate by only 1.86 pp, showing that process diagnosis can guide effective repair.

LEAP: Likelihood Elicitation and Aggregation for LLM-based Probabilistic Forecasting

This work proposes LEAP (Likelihood Elicitation and Aggregation for Probabilistic forecasting), which reorganizes how collected evidence is used in the prediction stage and improves most prediction and calibration metrics across models and remains stronger under controlled comparisons of prior access, inference budget,...

Remember-R1: Mitigating Long-Context Visual Forgetting through Reinforcement Learning

Remember-R1 is proposed, a reinforcement learning framework that mitigates long-context visual forgetting by applying process-level supervision directly on the original reasoning trajectory, demonstrating its effectiveness in mitigating long-context visual forgetting.

ARAC: Benchmarking Auto-Research's Alignment and Completeness on End-to-End Researchs

The rapid advancement of Auto-Research has surfaced a fundamental evaluation challenge: how can we measure the alignment, logical coherence, and evolutionary completeness of its research trajectory with human research behavior? We propose Auto-Research's Alignment and Completeness, ARAC-Bench: a Researcher-Mimicking Ev...

LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications

This work investigates LLM-based forecasting agents, meaning systems in which a language model contributes to a scored prediction about a future or currently unobserved target, and organizes architectures into three groups.

Attack-agnostic robust decentralized federated learning