10 papers
VAKRA: Evaluating Multi-Hop Reasoning Across APIs and Retrieval Under Tool-Use Policies
Ankita Rajaram Naik, Anupama Murthi, Benjamin Elder +6
Agents deployed in enterprise settings must reason across structured APIs and document collections, yet existing benchmarks evaluate these capabilities in isolation. We introduce V…
Adaptive Turn-Taking for Real-time Multi-Party Voice Agents
Soumyajit Mitra, Prabhat Pandey, Abhinav Jain +2
Turn-taking in multi-party spoken conversations remains a fundamental challenge for voice-based agents, particularly under dynamic floor competition and varying user expectations.…
MHA-RAG: Improving Efficiency, Accuracy, and Consistency by Encoding Exemplars as Soft Prompts
Abhinav Jain, Xinyu Yao, Thomas Reps +1
Adapting Foundation Models to new domains with limited training data is challenging and computationally expensive. While prior work has demonstrated the effectiveness of using doma…
End-to-End Text-to-SQL with Dataset Selection: Leveraging LLMs for Adaptive Query Generation
Anurag Tripathi, Vaibhav Patle, Abhinav Jain +4
Text-to-SQL bridges the gap between natural language and structured database language, thus allowing non-technical users to easily query databases. Traditional approaches model tex…
SIMCOPILOT: Evaluating Large Language Models for Copilot-Style Code Generation
Mingchao Jiang, Abhinav Jain, Sophia Zorek +1
We introduce SIMCOPILOT, a benchmark that simulates the role of large language models (LLMs) as interactive, "copilot"-style coding assistants. Targeting both completion (finishing…
DOPPLER: Dual-Policy Learning for Device Assignment in Asynchronous Dataflow Graphs
Xinyu Yao, Daniel Bourgeois, Abhinav Jain +5
We study the problem of assigning operations in a dataflow graph to devices to minimize execution time in a work-conserving system, with emphasis on complex machine learning worklo…
RAG-Modulo: Solving Sequential Tasks using Experience, Critics, and Language Models
Abhinav Jain, Chris Jermaine, Vaibhav Unhelkar
Large language models (LLMs) have recently emerged as promising tools for solving challenging robotic tasks, even in the presence of action and observation uncertainties. Recent LL…
Prompt Tuning Strikes Back: Customizing Foundation Models with Low-Rank Prompt Adaptation
Abhinav Jain, Swarat Chaudhuri, Thomas Reps +1
Parameter-Efficient Fine-Tuning (PEFT) has become the standard for customising Foundation Models (FMs) to user-specific downstream tasks. However, typical PEFT methods require stor…
GO-DICE: Goal-Conditioned Option-Aware Offline Imitation Learning via Stationary Distribution Correction Estimation
Abhinav Jain, Vaibhav Unhelkar
Offline imitation learning (IL) refers to learning expert behavior solely from demonstrations, without any additional interaction with the environment. Despite significant advances…
Two Timin': Repairing Smart Contracts With A Two-Layered Approach
Abhinav Jain, Ehan Masud, Michelle Han +5
Due to the modern relevance of blockchain technology, smart contracts present both substantial risks and benefits. Vulnerabilities within them can trigger a cascade of consequences…