10 papers
Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies
Han Zhou, Xingchen Wan, Ruoxi Sun +5
Large language models, employed as multiple agents that interact and collaborate with each other, have excelled at solving complex tasks. The agents are programmed with prompts tha…
SETS: Leveraging Self-Verification and Self-Correction for Improved Test-Time Scaling
Jiefeng Chen, Jie Ren, Xinyun Chen +4
Recent advancements in Large Language Models (LLMs) have created new opportunities to enhance performance on complex reasoning tasks by leveraging test-time computation. However, e…
Maestro: Self-Improving Text-to-Image Generation via Agent Orchestration
Xingchen Wan, Han Zhou, Ruoxi Sun +4
Text-to-image (T2I) models, while offering immense creative potential, are highly reliant on human intervention, posing significant usability challenges that often necessitate manu…
Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training
Maximillian Chen, Ruoxi Sun, Tomas Pfister +1
Large language models (LLMs), optimized through human feedback, have rapidly emerged as a leading paradigm for developing intelligent conversational assistants. However, despite th…
On the Role of Feedback in Test-Time Scaling of Agentic AI Workflows
Souradip Chakraborty, Mohammadreza Pourreza, Ruoxi Sun +8
Agentic AI workflows (systems that autonomously plan and act) are becoming widespread, yet their task success rate on complex tasks remains low. A promising solution is inference-t…
DynScaling: Efficient Verifier-free Inference Scaling via Dynamic and Integrated Sampling
Fei Wang, Xingchen Wan, Ruoxi Sun +2
Inference-time scaling has proven effective in boosting large language model (LLM) performance through increased test-time computation. Yet, its practical application is often hind…