7 papers
Plans Work in Mysterious Ways: Evaluating a Plan Mode for Spreadsheet Agents
Aayush Kumar, Avik Dutta, Sumit Gulwani +3
Plan Modes have become standard features in agentic programming tools, allowing users to gain transparency and control by working with the agent to develop a plan before task execu…
Improving Language Agents through BREW: Bootstrapping expeRientially-learned Environmental knoWledge
Shashank Kirtania, Param Biyani, Priyanshu Gupta +4
Large Language Model (LLM)-based agents are increasingly capable of complex, multi-step tasks such as GUI automation, tool use, and data manipulation, yet they cannot learn from ex…
SWE-Sharp-Bench: A Reproducible Benchmark for C# Software Engineering Tasks
Sanket Mhatre, Yasharth Bajpai, Sumit Gulwani +2
AI coding agents have shown great progress on Python software engineering benchmarks like SWE-Bench, and for other languages like Java and C in benchmarks like Multi-SWE-Bench. How…
STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with FeedBack
Shashank Kirtania, Naman Gupta, Priyanshu Gupta +7
Large Language Models (LLMs) often generate incorrect or outdated information, especially in low-resource settings or when dealing with private data. To address this, Retrieval-Aug…
ConDABench: Interactive Evaluation of Language Models for Data Analysis
Avik Dutta, Priyanshu Gupta, Hosein Hasanbeig +6
Real-world data analysis tasks often come with under-specified goals and unclean data. User interaction is necessary to understand and disambiguate a user's intent, and hence, esse…
Why AI Agents Still Need You: Findings from Developer-Agent Collaborations in the Wild
Aayush Kumar, Yasharth Bajpai, Sumit Gulwani +2
Software Engineering Agents (SWE agents) can autonomously perform development tasks on benchmarks like SWE Bench, but still face challenges when tackling complex and ambiguous real…