Paper Detail
Nicholas Edwards, Sebastian Schuster
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 propose an uncertainty-aware multi-agent scaffold that explicitly decouples underspecification detection from code execution. Our results demonstrate that this multi-agent system using OpenHands + Claude Sonnet 4.5 achieves a 69.40% task resolve rate, significantly outperforming a standard single-agent setup (61.20%) and closing the performance gap with agents operating on fully specified instructions. Furthermore, we find that the multi-agent system exhibits well-calibrated uncertainty, conserving queries on simple tasks while proactively seeking information on more complex issues. These findings indicate that current models can be turned into proactive collaborators, where agents independently recognize when to ask questions to elicit missing information in real-world, underspecified tasks.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{edwards2026ask,
title = {Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents},
author = {Nicholas Edwards and Sebastian Schuster},
year = {2026},
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},
url = {https://huggingface.co/papers/2603.26233},
keywords = {Large Language Model agents, underspecification, SWE-bench Verified, multi-agent scaffold, uncertainty-aware, code execution, OpenHands, Claude Sonnet 4.5, task resolve rate, well-calibrated uncertainty, code available, huggingface daily},
eprint = {2603.26233},
archiveprefix = {arXiv},
}
{}