4 citations · 7 across the 18 of their papers we have counts for
20 papers
BOReFT: Manifold Steering of Language Models for Black-box Optimization
Dhruv Agarwal, Rico Angell, Kavitha Srinivas +4
Language models are increasingly used as proposal models for black-box search, from program optimization to molecular design. Existing approaches typically improve proposals throug…
Baikal: Structured Search for Deep Research over Data Lakes
Dhruv Agarwal, Rishitha Guttapalle Mohan, Aarti Kumari +5
Deep research over data lakes requires an LLM agent to investigate evidence across thousands of heterogeneous tables and passages to synthesize a report. Existing methods perform i…
SemStruct: Contextualizing Semantic Embeddings with Structural Information for Schema Matching
Inwon Kang, Kavitha Srinivas, Nandana Mihindukulasooriya +4
Schema matching is a fundamental step in integrating heterogeneous data sources. While Pre-trained Language Models (PLMs) have revolutionized this task by capturing linguistic sema…
Planning in the LLM Era: Building for Reliability and Efficiency
Michael Katz, Harsha Kokel, Kavitha Srinivas +1
Growing attention to intelligent agents has put a spotlight on one of their central capabilities: planning. Early attempts to leverage large language models (LLMs) for planning rel…
Learning and Reusing Policy Decompositions for Hierarchical Generalized Planning with LLM Agents
Shirin Sohrabi, Haritha Ananthakrishnan, Harsha Kokel +2
We present a dynamic policy-learning approach that combines generalized planning and hierarchical task decomposition for LLM-based agents. Our method, Hierarchical Component Learni…
Model Space Reasoning as Search in Feedback Space for Planning Domain Generation
James Oswald, Daniel Obolensky, Volodymyr Varha +5
The generation of planning domains from natural language descriptions remains an open problem even with the advent of large language models and reasoning models. Recent work sugges…
Towards Universal Tabular Embeddings: A Benchmark Across Data Tasks
Liane Vogel, Kavitha Srinivas, Niharika D'Souza +3
Tabular foundation models aim to learn universal representations of tabular data that transfer across tasks and domains, enabling applications such as table retrieval, semantic sea…
Can AI autonomously build, operate, and use the entire data stack?
Arvind Agarwal, Lisa Amini, Sameep Mehta +2
Enterprise data management is a monumental task. It spans data architecture and systems, integration, quality, governance, and continuous improvement. While AI assistants can help…
Evaluating Joinable Column Discovery Approaches for Context-Aware Search
Harsha Kokel, Aamod Khatiwada, Tejaswini Pedapati +4
Joinable Column Discovery is a critical challenge in automating enterprise data analysis. While existing approaches focus on syntactic overlap and semantic similarity, there remain…
QueryGym: Step-by-Step Interaction with Relational Databases
Haritha Ananthakrishnan, Harsha Kokel, Kelsey Sikes +4
We introduce QueryGym, an interactive environment for building, testing, and evaluating LLM-based query planning agents. Existing frameworks often tie agents to specific query lang…
MiGrATe: Mixed-Policy GRPO for Adaptation at Test-Time
Peter Phan, Dhruv Agarwal, Kavitha Srinivas +3
Large language models (LLMs) are increasingly being applied to black-box optimization tasks, from program synthesis to molecule design. Prior work typically leverages in-context le…
TOPJoin: A Context-Aware Multi-Criteria Approach for Joinable Column Search
Harsha Kokel, Aamod Khatiwada, Tejaswini Pedapati +4
One of the major challenges in enterprise data analysis is the task of finding joinable tables that are conceptually related and provide meaningful insights. Traditionally, joinabl…
ACPBench Hard: Unrestrained Reasoning about Action, Change, and Planning
Harsha Kokel, Michael Katz, Kavitha Srinivas +1
The ACPBench dataset provides atomic reasoning tasks required for efficient planning. The dataset is aimed at distilling the complex plan generation task into separate atomic reaso…
Can Cross Encoders Produce Useful Sentence Embeddings?
Haritha Ananthakrishnan, Julian Dolby, Harsha Kokel +2
Cross encoders (CEs) are trained with sentence pairs to detect relatedness. As CEs require sentence pairs at inference, the prevailing view is that they can only be used as re-rank…
ACPBench: Reasoning about Action, Change, and Planning
Harsha Kokel, Michael Katz, Kavitha Srinivas +1
There is an increasing body of work using Large Language Models (LLMs) as agents for orchestrating workflows and making decisions in domains that require planning and multi-step re…
Automating Thought of Search: A Journey Towards Soundness and Completeness
Daniel Cao, Michael Katz, Harsha Kokel +2
Large language models (LLMs) are being used to solve planning problems that require search. Most of the literature uses LLMs as world models to define the search space, forgoing so…
TabSketchFM: Sketch-based Tabular Representation Learning for Data Discovery over Data Lakes
Aamod Khatiwada, Harsha Kokel, Ibrahim Abdelaziz +7
Enterprises have a growing need to identify relevant tables in data lakes; e.g. tables that are unionable, joinable, or subsets of each other. Tabular neural models can be helpful…
Out of style: Misadventures with LLMs and code style transfer
Karl Munson, Chih-Kai Ting, Serenity Wade +4
Like text, programs have styles, and certain programming styles are more desirable than others for program readability, maintainability, and performance. Code style transfer, howev…
Large Language Models as Planning Domain Generators
James Oswald, Kavitha Srinivas, Harsha Kokel +3
Developing domain models is one of the few remaining places that require manual human labor in AI planning. Thus, in order to make planning more accessible, it is desirable to auto…
Thought of Search: Planning with Language Models Through The Lens of Efficiency
Michael Katz, Harsha Kokel, Kavitha Srinivas +1
Among the most important properties of algorithms investigated in computer science are soundness, completeness, and complexity. These properties, however, are rarely analyzed for t…