7 papers
Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning
Xin Cheng, Shuo He, Lang Feng +4
Group-based reinforcement learning (RL) methods have achieved remarkable success in improving the performance of large language models (LLMs) and have been rapidly extended to agen…
Transformers Can Implement Preconditioned Richardson Iteration for In-Context Gaussian Kernel Regression
Mingsong Yan, Dongyang Li, Charles Kulick +1
Mechanistic accounts of in-context learning (ICL) have identified iterative algorithms for linear regression and related linear prediction tasks, often using linear or ReLU attenti…
ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
Xuhao Hu, Xi Zhang, Haiyang Xu +6
Computer Use Agents (CUAs) can act through both atomic GUI actions, such as click and type, and high-level tool calls, such as API-based file operations, but this hybrid action spa…
Seeing Straight: Document Orientation Detection for Efficient OCR
Suranjan Goswami, Abhinav Ravi, Raja Kolla +5
Despite significant advances in document understanding, determining the correct orientation of scanned or photographed documents remains a critical pre-processing step in the real…
AgentOCR: Reimagining Agent History via Optical Self-Compression
Lang Feng, Fuchao Yang, Feng Chen +5
Recent advances in large language models (LLMs) enable agentic systems trained with reinforcement learning (RL) over multi-turn interaction, but practical deployment is bottlenecke…
Efficient and Effective In-context Demonstration Selection with Coreset
Zihua Wang, Jiarui Wang, Haiyang Xu +6
In-context learning (ICL) has emerged as a powerful paradigm for Large Visual Language Models (LVLMs), enabling them to leverage a few examples directly from input contexts. Howeve…