Moves coding agents from passive execution to proactive collaboration by teaching them when to ask for clarification on underspecified tasks.
March 30, 2026
Original Paper
Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents
arXiv · 2603.26233
The Takeaway
Current agents often fail by making assumptions about missing context; this multi-agent scaffold decouples detection from execution, achieving a 69.4% resolve rate on SWE-bench Verified. It provides a blueprint for building autonomous systems that are safer and more effective in real-world, ambiguous software environments.
From the abstract
As Large Language Model (LLM) agents are increasingly deployed in open-ended domains like software engineering, they frequently encounter underspecified instructions that lack crucial context. While human developers naturally resolve underspecification by asking clarifying questions, current agents are largely optimized for autonomous execution. In this work, we systematically evaluate the clarification-seeking abilities of LLM agents on an underspecified variant of SWE-bench Verified. We propos