activity
20242026
collaborators

6 papers

cs.AI2026

Tokengeist: Multi-Turn Attribution Tracing in Agentic Conversations

Jessica Tang, Shraddha Barke, Sharad Agarwal

When a language model produces a response in a multi-turn conversation, which tokens from prior turns shaped that answer, and how did those dependencies propagate across prior turn…

cs.SE2026

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…

cs.SE2026

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…

cs.AI2026

AgentRx: Diagnosing AI Agent Failures from Execution Trajectories

Shraddha Barke, Arnav Goyal, Alind Khare +3

AI agents often fail in ways that are difficult to localize because executions are probabilistic, long-horizon, multi-agent, and mediated by noisy tool outputs. We address this gap…

cs.SE2025

What's in a Proof? Analyzing Expert Proof-Writing Processes in F* and Verus

Rijul Jain, Shraddha Barke, Gabriel Ebner +3

Proof-oriented programming languages (POPLs) empower developers to write code alongside formal correctness proofs, providing formal guarantees that the code adheres to specified re…

cs.PL2024

HYSYNTH: Context-Free LLM Approximation for Guiding Program Synthesis

Shraddha Barke, Emmanuel Anaya Gonzalez, Saketh Ram Kasibatla +2

Many structured prediction and reasoning tasks can be framed as program synthesis problems, where the goal is to generate a program in a domain-specific language (DSL) that transfo…