Zhao, Jun

Large Language Models for Planning: A Comprehensive and Systematic Survey

Planning represents a fundamental capability of intelligent agents, requiring comprehensive environmental understanding, rigorous logical reasoning, and effective sequential decision-making. While...

InfoFlow: Reinforcing Search Agent Via Reward Density Optimization

Reinforcement Learning with Verifiable Rewards (RLVR) is a promising approach for enhancing agentic deep search. However, its application is often hindered by low \textbf{Reward Density} in deep...

Amplify Adjacent Token Differences: Enhancing Long Chain-of-Thought Reasoning with Shift-FFN

Recently, models such as OpenAI-o1 and DeepSeek-R1 have demonstrated remarkable performance on complex reasoning tasks through Long Chain-of-Thought (Long-CoT) reasoning. Although distilling this...

MemTools: A Unified Research Framework for Interoperable Agent Memory

SkillPyramid: A Hierarchical Skill Consolidation Framework for Self-Evolving Agents

Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies

Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent

Case-based Statute Retrieval for Multi-turn Legal Consultation with Fact-level and Rationale-level Mixed Evidence Graphs

ExpRL: Unified Non-Parametric and Parametric Experience Learning for LLM Agent Evolution

From Perception to Simulation: Unveiling and Empowering Mental Spatial Dynamics in MLLMs

When Retrieval Partially Conflicts with Skills: Understanding Procedural Hallucination in Language Models

Neural Procedural Memory: Empowering LLM Agents with Implicit Activation Steering

SwarmBench: Can Large Language Models Act as Agent Swarm Orchestrators?

RuleWeaver: Benchmarking Rule-Centered Scenario Reasoning for Large Language Models

Beyond Factual Knowledge: Benchmarking and Learning Step-Level Procedural Rule Reasoning in Large Language Models

Quantifying Error Tolerance in Synthetic Data: An Atomic-level Operand vs. Operator Perturbation Study

A Quasi-Dependency Model for Structural Analysis it of Chinese BaseNPs

A Quasi-Dependency Model for the Structural Analysis of Chinese BaseNPs