9 papers
OpenForgeRL: Train Harness-native Agents in Any Environment
Xiao Yu, Baolin Peng, Ruize Xu +7
Modern AI agents rely on elaborate inference harnesses such as Claude Code, Codex, and OpenClaw to drive multi-turn reasoning, tool use, and access to external systems. While power…
DMV-Bench: Diagnosing Long-Horizon Multimodal Agents' Visual Memory with Incidental Cue Injection
Yujin Tang, Chenming Shang, Ruize Xu +1
Research on agent memory has matured rapidly, but almost entirely on the text side: few existing benchmarks ask, in an interactive environment, when an agent genuinely needs to rem…
ConFit v3: Improving Resume-Job Matching with LLM-based Re-Ranking
Xiao Yu, Ruize Xu, Chengyuan Xue +6
A reliable resume-job matching system helps a company find suitable candidates from a pool of resumes and helps a job seeker find relevant jobs from a list of job posts. While rece…
Training Transformers as a Universal Computer
Ruize Xu, Chenxiao Yang, Yanhong Li +1
We demonstrate that a small transformer can learn to execute programs in MicroPy, a simplified yet computationally universal programming language. Given procedure definitions toget…
Teaching an Agent to Sketch One Part at a Time
Xiaodan Du, Ruize Xu, David Yunis +2
We develop a method for producing vector sketches one part at a time. To do this, we train a multi-modal language model-based agent using a novel multi-turn process-reward reinforc…
Reinforcement World Model Learning for LLM-based Agents
Xiao Yu, Baolin Peng, Ruize Xu +6
Large language models (LLMs) have achieved strong performance in language-centric tasks. However, in agentic settings, LLMs often struggle to anticipate action consequences and ada…