Yangning Li

Process-Level Trajectory Evaluation for Environment Configuration in Software Engineering Agents

Adversarial Encoding Perturbation and Synthesis for Set Representation Auxiliary Learning

RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback

PSG-Agent: Personality-Aware Safety Guardrail for LLM-based Agents

DeepResearchGuard: Deep Research with Open Domain Evaluation and Multi-Stage Guardrails for Safety

Atomic Thinking of LLMs: Decoupling and Exploring Mathematical Reasoning Abilities

AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees

Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent

Refine Knowledge of Large Language Models via Adaptive Contrastive Learning

One Example Shown, Many Concepts Known! Counterexample-Driven Conceptual Reasoning in Mathematical LLMs