paper-with-me

Papers

Interactive Agents to Overcome Ambiguity in Software Engineering

2025-02-18 · Sanidhya Vijayvargiya, Xuhui Zhou, Akhila Yerukola, Maarten Sap, Graham Neubig

AI agents are increasingly being deployed to automate tasks, often based on ambiguous and underspecified user instructions. Making unwarranted assumptions and failing to ask clarifying questions can lead to suboptimal outcomes, safety risks due to tool misuse, and wasted computational resources. In this work, we study the ability of LLM agents to handle ambiguous instructions in interactive code generation settings by evaluating proprietary and open-weight models on their performance across three key steps: (a) leveraging interactivity to improve performance in ambiguous scenarios, (b) detecting ambiguity, and (c) asking targeted questions. Our findings reveal that models struggle to distinguish between well-specified and underspecified instructions. However, when models interact for underspecified inputs, they effectively obtain vital information from the user, leading to significant improvements in performance and underscoring the value of effective interaction. Our study highlights critical gaps in how current state-of-the-art models handle ambiguity in complex software engineering tasks and structures the evaluation into distinct steps to enable targeted improvements.

📄 PDF Abstract BibTeX arXiv:2502.13069

Code (1)

sani903/interactivesweagents 공식 구현

Tasks

Code Generation

Similar Papers 제목 키워드 기반

SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents

2025-05-26 · Ibragim Badertdinov, Alexander Golubev, Maksim Nekrashevich, Anton Shevtsov 외

LLM-based agents have shown promising capabilities in a growing range of software engineering (SWE) tasks. However, advancing this field faces two critical challenges. First, high-quality training data is scarce, especia…

Code Generation

LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering

2025-11-17 · Jielin Qiu, Zuxin Liu, Zhiwei Liu, Rithesh Murthy 외 arxiv

As large language models (LLMs) evolve into sophisticated autonomous agents capable of complex software development tasks, evaluating their real-world capabilities becomes critical. While existing benchmarks like LoCoBen…

Dialogue SWE-Bench: A Benchmark for Dialogue-Driven Coding Agents

2026-06-12 · Brendan King, Jeffrey Flanigan arxiv

AI coding agents have rapidly transformed software engineering, powering widely used interactive coding assistants. Despite their interactive real-world use, existing benchmarks evaluate them as fully-autonomous systems.…

SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering

2024-05-06 · John Yang, Carlos E. Jimenez, Alexander Wettig, Kilian Lieret 외

Language model (LM) agents are increasingly being used to automate complicated tasks in digital environments. Just as humans benefit from powerful software applications, such as integrated development environments, for c…

Bug fixingLanguage ModelingLanguage ModellingNavigate

Software Engineering Agents for Embodied Controller Generation : A Study in Minigrid Environments

2025-10-24 · Timothé Boulet, Xavier Hinaut, Clément Moulin-Frier arxiv

Software Engineering Agents (SWE-Agents) have proven effective for traditional software engineering tasks with accessible codebases, but their performance for embodied tasks requiring well-designed information discovery …