Junfeng Fang

The paper proposes TRACE, a trajectory risk-aware compression method, to effectively aggregate sparse and delayed safety evidence across long agent trajectories, achieving state-of-the-art performance on multiple safety benchmarks.

The paper introduces Unified Context Evolution (UCE), a gradient-free framework that externalizes and manages agent experience into a typed, evolving library, significantly improving performance on multi-step interactive tasks.

ResMerge proposes a residual-based spectral merging framework that improves the combination of multiple reinforcement learning (RL) expert models by stabilizing the aggregation process using a residual backbone.