6 papers
Revisiting Observation Reduction for Web Agents: Comprehensive Evaluation with a Lightweight Framework
Masafumi Enomoto, Ryoma Obara, Haochen Zhang +1
HTML observations in LLM-based web agents are extremely long, and while many reduction methods have been proposed, it remains unclear which methods reduce overall agent latency whi…
Effective Harness Engineering for Algorithm Discovery with Coding Agents
Yoichi Ishibashi, Taro Yano, Masafumi Oyamada
AlphaEvolve and FunSearch have demonstrated the potential of combining large language models (LLMs) with evolutionary search for automated algorithm discovery. However, discovery s…
cotomi Act: Learning to Automate Work by Watching You
Masafumi Oyamada, Kunihiro Takeoka, Kosuke Akimoto +5
What if a browser agent could learn your work simply by watching you do it? We present cotomi Act, a browser-based computer-using agent that combines reliable multi-step task execu…
Read More, Think More: Revisiting Observation Reduction for Web Agents
Masafumi Enomoto, Ryoma Obara, Haochen Zhang +1
Web agents based on large language models (LLMs) rely on observations of web pages -- commonly represented as HTML -- as the basis for identifying available actions and planning su…
DISC: Dynamic Decomposition Improves LLM Inference Scaling
Jonathan Light, Wei Cheng, Benjamin Riviere +6
Inference scaling methods for LLMs often rely on decomposing problems into steps (or groups of tokens), followed by sampling and selecting the best next steps. However, these steps…
Understanding the Impact of Confidence in Retrieval Augmented Generation: A Case Study in the Medical Domain
Shintaro Ozaki, Yuta Kato, Siyuan Feng +8
Retrieval Augmented Generation (RAG) complements the knowledge of Large Language Models (LLMs) by leveraging external information to enhance response accuracy for queries. This app…