5 papers
Learning Context-Free Grammars for Grammar-Constrained Decoding via Declarative Agentic Programming with Guarantees
Kevin Cheang, Geoff Hulette, Rahul Kumar +5
Language models (LMs) are increasingly used to interact with external services via programs written in domain-specific languages (DSLs). Unfortunately, since DSLs are often low-res…
Learning Affordances at Inference-Time for Vision-Language-Action Models
Ameesh Shah, William Chen, Adwait Godbole +3
Solving complex real-world control tasks often takes multiple tries: if we fail at first, we reflect on what went wrong, and change our strategy accordingly to avoid making the sam…
Online Prompt Selection for Program Synthesis
Yixuan Li, Lewis Frampton, Federico Mora +1
Large Language Models (LLMs) demonstrate impressive capabilities in the domain of program synthesis. This level of performance is not, however, universal across all tasks, all LLMs…
Synthetic Programming Elicitation for Text-to-Code in Very Low-Resource Programming and Formal Languages
Federico Mora, Justin Wong, Haley Lepe +6
Recent advances in large language models (LLMs) for code applications have demonstrated remarkable zero-shot fluency and instruction following on challenging code related tasks ran…
An Eager Satisfiability Modulo Theories Solver for Algebraic Datatypes
Amar Shah, Federico Mora, Sanjit A. Seshia
Algebraic data types (ADTs) are a construct classically found in functional programming languages that capture data structures like enumerated types, lists, and trees. In recent ye…