5 papers
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…
IndiMathBench: Autoformalizing Mathematical Reasoning Problems with a Human Touch
Param Biyani, Shashank Kirtania, Yasharth Bajpai +2
Reliable autoformalization remains challenging even in the era of large language models (LLMs). The scarcity of high-quality training data is a major bottleneck. Expert annotation…
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…
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…
TableTalk: Scaffolding Spreadsheet Development with a Language Agent
Jenny T. Liang, Aayush Kumar, Yasharth Bajpai +7
Spreadsheet programming is challenging. Programmers use spreadsheet programming knowledge (e.g., formulas) and problem-solving skills to combine actions into complex tasks. Advance…