activity
20242026
collaborators

7 papers

cs.HC2026

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…

cs.AI2026

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…

cs.SE2025

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…

cs.AI2025

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Large Language Models (LLMs) often generate incorrect or outdated information, especially in low-resource settings or when dealing with private data.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…

cs.CL2025

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…

cs.SE2025

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…