Fei Cheng

The paper introduces AutoEG, a fully automated multi-agent framework that significantly improves the exploitation of known third-party vulnerabilities in black-box web applications by achieving an 82.41% average success rate.

The paper investigates anthropomorphic reflection markers (like 'hmm' or 'wait') in LLM reasoning and finds that these markers are often surface cues, not necessary for strong reasoning performance.

This paper introduces the Data-Model Compatibility (DMC) metric to quantify how suitable a dataset is for reasoning distillation, showing that optimizing data selection using DMC significantly improves the performance of smaller student models.

The paper introduces BenchTrace, a novel benchmark designed to rigorously evaluate the self-evolution and reflection capabilities of LLM agents, revealing that current models struggle with accurate failure diagnosis and generalizing learned lessons.

The paper proposes a novel symmetry-aware, category-level method for 9D object pose estimation that accurately estimates translation and size first, followed by rotation, achieving state-of-the-art results on diverse objects.

The paper identifies a failure mode called spatial lexical bias in MLLMs, where adding a spatial word to options biases the model's choice, and demonstrates that this failure originates primarily from the language processing side rather than poor visual attention.