6 papers
Agent Lifecycle Toolkit (ALTK): Reusable Middleware Components for Robust AI Agents
Zidane Wright, Jason Tsay, Anupama Murthi +8
As AI agents move from demos into enterprise deployments, their failure modes become consequential: a misinterpreted tool argument can corrupt production data, a silent reasoning e…
When Agents go Astray: Course-Correcting SWE Agents with PRMs
Shubham Gandhi, Jason Tsay, Jatin Ganhotra +2
Large Language Model (LLM) agents are increasingly deployed for complex, multi-step software engineering (SWE) tasks. However, their trajectories often contain costly inefficiencie…
Repairing Tool Calls Using Post-tool Execution Reflection and RAG
Jason Tsay, Zidane Wright, Gaodan Fang +3
Agentic systems interact with external systems by calling tools such as Python functions, REST API endpoints, or command line tools such as kubectl in Kubernetes. These tool calls…
OASBuilder: Generating OpenAPI Specifications from Online API Documentation with Large Language Models
Koren Lazar, Matan Vetzler, Kiran Kate +8
AI agents and business automation tools interacting with external web services require standardized, machine-readable information about their APIs in the form of API specifications…
Improving Examples in Web API Specifications using Iterated-Calls In-Context Learning
Kush Jain, Kiran Kate, Jason Tsay +2
Examples in web API specifications can be essential for API testing, API understanding, and even building chat-bots for APIs. Unfortunately, most API specifications lack human-writ…
Towards LLMs Robustness to Changes in Prompt Format Styles
Lilian Ngweta, Kiran Kate, Jason Tsay +1
Large language models (LLMs) have gained popularity in recent years for their utility in various applications. However, they are sensitive to non-semantic changes in prompt formats…