26 papers
Reason Wide, Not Deep: Amortizing the Reasoning Premium into Distilled Skills
Agamdeep Singh, Srishti Gautam, Priyanshu Gupta +3
Reasoning modes of language models outperform their non-reasoning counterparts on multi-step agentic tasks, but pay a 3-6x premium in output tokens on every episode -- much of it s…
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…
A Benchmark and Framework for Evaluating Next Action Predictions in Spreadsheets
Tejas Agrawal, Vu Le, Sumit Gulwani +1
Predictive code completion greatly accelerates how quickly developers work. In spreadsheets, despite being much more common, such auto-completion features are virtually non-existen…
SkillAxe: Sharpening LLM-Authored Agent Skills Through Evaluation-Guided Self-Refinement
Srishti Gautam, Arjun Radhakrishna, Sumit Gulwani
Skill documents, structured natural-language instructions that guide Large Language Model (LLM) agents, are critical to modern agent frameworks, yet LLMs struggle to write skills t…
Auditing and Controlling AI Agent Actions in Spreadsheets
Sadra Sabouri, Zeinabsadat Saghi, Run Huang +4
Advances in AI agent capabilities have outpaced users' ability to meaningfully oversee their execution. AI agents can perform sophisticated, multi-step knowledge work autonomously…