Qihan Ren

Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents

Conditional Advantage Estimation for Reinforcement Learning in Large Reasoning Models

Towards Self-Evolving Agent Benchmarks : Validatable Agent Trajectory via Test-Time Exploration

Can LLMs Reason Soundly in Law? Auditing Inference Patterns for Legal Judgment

Towards the Decisive Factor of Symbolic Generalization of DNNs

Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution

Formulating Generalizable and Non-Generalizable Interactions in DNNs

Towards the Dynamics of Representation Changes during Parameter Pruning for Network Compression

Where We Have Arrived in Proving the Emergence of Sparse Interaction Primitives in DNNs

Towards the Dynamics of a DNN Learning Symbolic Interactions