7 papers
Willful Disobedience: Automatically Detecting Failures in Agentic Traces
Reshabh K Sharma, Shraddha Barke, Benjamin Zorn
AI agents are increasingly embedded in real software systems, where they execute multi-step workflows through multi-turn dialogue, tool invocations, and intermediate decisions. The…
Learning Correct Behavior from Examples: Validating Sequential Execution in Autonomous Agents
Reshabh K Sharma, Gaurav Mittal, Yu Hu
As autonomous agents become increasingly sophisticated, validating their sequential behavior presents a significant challenge. Traditional testing approaches require manual specifi…
ContextCov: Deriving and Enforcing Executable Constraints from Agent Instruction Files
Reshabh K Sharma
As Large Language Model (LLM) agents increasingly execute complex, autonomous software engineering tasks, developers rely on natural language instruction files such as AGENTS.md to…
AC4A: Access Control for Agents
Reshabh K Sharma, Dan Grossman
Large Language Model (LLM) agents combine the chat interaction capabilities of LLMs with the power to interact with external tools and APIs. This enables them to perform complex ta…
Beyond OAuth: Task-Scoped Authorization for AI Agents via Natural Language Slices
Reshabh K Sharma, Linxi Jiang, Zhiqiang Lin +1
AI agents increasingly execute users' natural-language (NL) tasks by calling Web services, yet today's Web authorizes these calls through OAuth, which grants permissions over opera…
PromptPex: Automatic Test Generation for Language Model Prompts
Reshabh K Sharma, Jonathan De Halleux, Shraddha Barke +2
Large language models (LLMs) are being used in many applications and prompts for these models are integrated into software applications as code-like artifacts. These prompts behave…