7 papers
Actionable Hallucination Detection: Translating Latent Uncertainty into Agentic Critique
Sanidhya Vijayvargiya, Rahul Lokesh
Large Language Models (LLMs) deployed as AI agents frequently exhibit user specification-grounding failures, executing hallucinated, undesired actions to force a resolution rather…
Asking What Matters: Reward-Driven Clarification for Software Engineering Tasks
Sanidhya Vijayvargiya, Vijay Viswanathan, Graham Neubig
Humans often specify tasks incompletely, so assistants must know when and how to ask clarifying questions. However, effective clarification remains challenging in software engineer…
CodeScout: An Effective Recipe for Reinforcement Learning of Code Search Agents
Lintang Sutawika, Aditya Bharat Soni, Bharath Sriraam R R +8
A prerequisite for coding agents to perform tasks on large repositories is code localization - the identification of relevant files, classes, and functions to work on. While reposi…
How Well Does Agent Development Reflect Real-World Work?
Zora Zhiruo Wang, Sanidhya Vijayvargiya, Aspen Chen +7
AI agents are increasingly developed and evaluated on benchmarks relevant to human work, yet it remains unclear how representative these benchmarking efforts are of the labor marke…
Ambig-SWE: Interactive Agents to Overcome Underspecificity in Software Engineering
Sanidhya Vijayvargiya, Xuhui Zhou, Akhila Yerukola +2
AI agents are increasingly being deployed to automate tasks, often based on underspecified user instructions. Making unwarranted assumptions to compensate for the missing informati…
OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety
Sanidhya Vijayvargiya, Aditya Bharat Soni, Xuhui Zhou +4
Recent advances in AI agents capable of solving complex, everyday tasks, from scheduling to customer service, have enabled deployment in real-world settings, but their possibilitie…