2 citations · 2 across the 17 of their papers we have counts for
22 papers
AutoEnvScaling: Automating the Data Flywheel with Terminal Agents
Simon Yu, Baolin Peng, Bo Liu +8
Terminal agents solve tasks in software engineering and scientific research by executing commands in a terminal. Training them via reinforcement learning (RL) requires diverse and…
SecureVibe: Making Vibe Coding More Secure
Danqing Wang, Baolin Peng, Zhepei Wei +8
As vibe coding becomes increasingly capable and widespread, security vulnerabilities in even functionally correct solutions are a growing concern. When investigating functionally c…
Certified Long-Horizon Code Agent Evolution via Validation-Gated Skill Optimization
Yifan Wang, Hao Cheng, Xiaomin Li +13
Long horizon agent self-evolution without model weight updates is essential for enabling deployed agents to accumulate reusable skills and improve over time. Prior self-evolution w…
ExecCritic: Learn to Test, Test to Improve for Coding Agents
Leitian Tao, Baolin Peng, Haorui Wang +7
Execution feedback can guide coding agents toward correct repository repairs, but only when the tests capture the behavior requested by the issue. Agent-generated tests can encode…
ARISE-RL: Agentic Rubric-Grounded Iterative Self-Evolution with Reinforcement Learning
Fanrui Zhang, Ruixue Ding, Qiang Zhang +13
Training open-ended agents via reinforcement learning (RL) is hindered by the lack of verifiable gold answers and scalable rubrics. Moreover, even near the model's capability bound…
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…
TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents
Leitian Tao, Baolin Peng, Wenlin Yao +5
Multi-turn agents solve complex tasks through extended sequences of tool interactions before producing a final answer, making credit assignment a fundamental challenge during post-…
LEDGER: Scaling Agentic Document Editing with Dependency-aware Graph Retrieval
Mike Hang Wang, Utkarsh Garg, Reza Davari +5
We introduce LEDGER to tackle the novel context engineering challenge of agentic document editing, where localized edits to long, structured documents must be applied efficiently w…
OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents
Rui Yang, Qianhui Wu, Yuxi Chen +7
Building capable visual web agents requires long-horizon reasoning, precise grounding, and robust interaction with dynamic real-world websites. Despite rapid progress, the stronges…
Synthetic Computers at Scale for Long-Horizon Productivity Simulation
Tao Ge, Baolin Peng, Hao Cheng +1
Realistic long-horizon productivity work is strongly conditioned on user-specific computer environments, where much of the work context is stored and organized through directory st…
The Tool Illusion: Rethinking Tool Use in Web Agents
Renze Lou, Baolin Peng, Wenlin Yao +5
As web agents rapidly evolve, an increasing body of work has moved beyond conventional atomic browser interactions and explored tool use as a higher-level action paradigm. Although…
GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL
Rui Yang, Qianhui Wu, Zhaoyang Wang +8
Open-source native GUI agents still lag behind closed-source systems on long-horizon navigation tasks. This gap stems from two limitations: a shortage of high-quality, action-align…
Multimodal Reinforcement Learning with Adaptive Verifier for AI Agents
Reuben Tan, Baolin Peng, Zhengyuan Yang +15
Agentic reasoning models trained with multimodal reinforcement learning (MMRL) have become increasingly capable, yet they are almost universally optimized using sparse, outcome-bas…
Dyna-Mind: Learning to Simulate from Experience for Better AI Agents
Xiao Yu, Baolin Peng, Michel Galley +6
Reasoning models have recently shown remarkable progress in domains such as math and coding. However, their expert-level abilities in math and coding contrast sharply with their pe…
SAS: Simulated Attention Score
Chuanyang Zheng, Jiankai Sun, Yihang Gao +12
The attention mechanism is a core component of the Transformer architecture. Various methods have been developed to compute attention scores, including multi-head attention (MHA),…
Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents
Xiao Yu, Baolin Peng, Ruize Xu +5
Recent progress in reasoning with large language models (LLMs), such as DeepSeek-R1, demonstrates impressive capabilities in domains like mathematics and coding, by exhibiting comp…
Reinforcement Learning for Reasoning in Large Language Models with One Training Example
Yiping Wang, Qing Yang, Zhiyuan Zeng +11
We show that reinforcement learning with verifiable reward using one training example (1-shot RLVR) is effective in incentivizing the math reasoning capabilities of large language…
On Memory Construction and Retrieval for Personalized Conversational Agents
Zhuoshi Pan, Qianhui Wu, Huiqiang Jiang +8
To deliver coherent and personalized experiences in long-term conversations, existing approaches typically perform retrieval augmented response generation by constructing memory ba…
CollabLLM: From Passive Responders to Active Collaborators
Shirley Wu, Michel Galley, Baolin Peng +7
Large Language Models are typically trained with next-turn rewards, limiting their ability to optimize for long-term interaction. As a result, they often respond passively to ambig…
Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities
Chung-En Sun, Xiaodong Liu, Weiwei Yang +5
Recent research has shown that Large Language Models (LLMs) are vulnerable to automated jailbreak attacks, where adversarial suffixes crafted by algorithms appended to harmful quer…
ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning
Xiao Yu, Baolin Peng, Vineeth Vajipey +4
Autonomous agents have demonstrated significant potential in automating complex multistep decision-making tasks. However, even state-of-the-art vision-language models (VLMs), such…
Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering
Qingru Zhang, Xiaodong Yu, Chandan Singh +6
Large language models (LLMs) have demonstrated remarkable performance across various real-world tasks. However, they often struggle to fully comprehend and effectively utilize thei…