34 citations · 65 across the 10 of their papers we have counts for
12 papers
Understanding Enrichment in Reinforcement Learning
Jinwoo Kim, Shraddha Barke
When rewards are sparse, reinforcement learning with verifiable rewards (RLVR) often uses hints or intermediate guidance to generate more successful rollouts. This enrichment biase…
Agents as Software: A Programming Languages Agenda for Agent Reliability
Shraddha Barke, Adithya Murali
AI agents increasingly resemble software systems: they call tools, remember facts, follow policies, delegate work, and take actions with real consequences. % Yet the ``program'' of…
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…
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…
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…
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…
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…
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…
Solving Data-centric Tasks using Large Language Models
Shraddha Barke, Christian Poelitz, Carina Suzana Negreanu +10
Large language models (LLMs) are rapidly replacing help forums like StackOverflow, and are especially helpful for non-professional programmers and end users. These users are often…
Grounded Copilot: How Programmers Interact with Code-Generating Models
Shraddha Barke, Michael B. James, Nadia Polikarpova
Powered by recent advances in code-generating models, AI assistants like Github Copilot promise to change the face of programming forever. But what is this new face of programming?…
Just-in-Time Learning for Bottom-Up Enumerative Synthesis
Shraddha Barke, Hila Peleg, Nadia Polikarpova
A key challenge in program synthesis is the astronomical size of the search space the synthesizer has to explore. In response to this challenge, recent work proposed to guide synth…
Targeted Synthesis for Programming with Data Invariants
John Sarracino, Shraddha Barke, Hila Peleg +2
Programmers frequently maintain implicit data invariants, which are relations between different data structures in a program. Traditionally, such invariants are manually enforced a…