-
SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents
Paper • 2508.02085 • Published • 2 -
RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving
Paper • 2505.21577 • Published • 3 -
GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging
Paper • 2508.18993 • Published • 4
AI & ML interests
Code Agent | DeepSearch
Recent Activity
View all activity
Papers
Controlled Self-Evolution for Algorithmic Code Optimization
Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning
-
SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents
Paper • 2508.02085 • Published • 2 -
RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving
Paper • 2505.21577 • Published • 3 -
GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging
Paper • 2508.18993 • Published • 4
models
0
None public yet
datasets
0
None public yet