arXiv Computation and Language

From Abstraction to Action: DSLs for Natural Language Abstraction Interpretation and Execution

The paper introduces domain-specific languages (DSLs) as an explicit representation layer to bridge the gap between high-level natural-language abstractions and concrete actions. Experiments on the visually-grounded “Hexagons” task and the “Text2CAD” benchmark show that code generation using a human-curated DSL yields dramatic performance gains, especially at higher abstraction levels, while automatically induced DSLs only partially recover these gains. The study highlights that the right representation can close much of the performance gap caused by abstraction, but that automatically learning such representations remains a challenge.

arXiv AI

Sep 1

Imag-Eval: a language-grounded framework for interpretable Text-to-Image instruction following evaluation

Imag‑Eval is a new language‑grounded benchmark for evaluating Text‑to‑Image models, focusing on how well they follow compositional natural‑language instructions. It disentangles prompt length from compositional difficulty by independently varying the number of instances and the combination of constraints (rules), providing 1,140 prompts and 8,842 rule combinations. The study shows that for structured skills, the difficulty is mainly driven by the number of grounded rules and their binding to instances rather than prompt length alone.

By Ibrahim Mohamed Serouis, David Jaramillo Duque

diffusion multimodal benchmarks

arXiv AI

Sep 28

Up and Down the Abstraction Ladder: Code-Based Skills for Language Agents

The paper introduces CodeHack, a library of code-based skills with natural-language descriptions designed to improve language agents in complex environments like NetHack. By allowing agents to invoke reusable skills instead of selecting individual actions, the study shows that skill-based agents nearly triple game progression and cut inference cost by 86% in zero‑shot settings, while still retaining the option to fall back on primitive actions. In reinforcement learning, skill-based agents learn faster, achieving a 7.2× larger average gain in dungeon level within the same training budget.

By Bart{\l}omiej Cupia{\l}, Jens Tuyls, Maciej Wo{\l}czyk, Davide Paglieri, Martin Klissarov, Benjamin Eysenbach, Piotr Mi{\l}o\'s, Karthik R. Narasimhan

llms agents reinforcement-learning fine-tuning

arXiv AI

Sep 30

LLMs are not stochastic parrots: Evidence for meaning-mediated abstraction from conlang-like tasks

arXiv:2609.34187v2 Announce Type: replace-cross Abstract: The strong version of the stochastic parrot argument claims that, although large language models (LLMs) may exceed rote regurgitation, they c...

By Julia Witte Zimmerman, Calla G. Beauregard, Tabia Tanzin Prama, Parisa Suchdev, Kathryn Cramer, Elisabeth Kollrack

llms

arXiv Machine Learning

Oct 2

Lasting Effects of Abstract Pretraining Beyond Perplexity

arXiv:2609.38764v1 Announce Type: new Abstract: Language models are typically pretrained from random initialization. Recent work challenges this convention, showing that a brief warm-up on abstract,...

By Zachary Shinnick, Hemanth Saratchandran, Damien Teney, Anton van den Hengel

llms nlp robotics

arXiv Machine Learning

Jul 10

Prompt Compression via Activation Aggregation

arXiv:2607. 08399v1 Announce Type: cross Abstract: Large language models process prompts by propagating activations through dozens of layers before generating a response.

By Thibaud Ardoin, Semira Einsele, Evis Bregu, Gerhard Wunder

llms

arXiv AI

Sep 15

Testing the Limits of Truth Directions in LLMs

arXiv:2604.03754v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have been shown to encode truth of statements in their activation space along a linear truth direction. Previous...

By Angelos Poulis, Mark Crovella, Evimaria Terzi

llms

Hugging Face Trending Papers

Aug 31

Autoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language Models

Large language models (LLMs) trained only on text and code can sometimes generate programs that draw recognizable images. However, it is unclear whether this reflects an internal representation of 2D...

llms benchmarks

arXiv Computer Vision

Oct 8

From Pixel to Coding: Evaluating the Figure Reproduction Capabilities of MLLMs

arXiv:2610.10066v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in both visual understanding and code generation. However, existing...

By Zijian Chen, Zhengyu Chen, Bohan Liang, Lirong Deng, Yushuo Zheng, Yanwei Jiang, Qi Jia, Kaiwei Zhang, Wenjun Zhang, Guangtao Zhai

llms multimodal benchmarks

arXiv AI

Sep 1

Autoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language Models

arXiv:2608.30751v1 Announce Type: new Abstract: Large language models (LLMs) trained only on text and code can sometimes generate programs that draw recognizable images. However, it is unclear whethe...

By Ashwin Nedungadi, Stefan Oehmcke, Stefan L\"udtke

llms benchmarks

Hugging Face Trending Papers

2d ago

Verbalizing Activation Differences with Natural Language Autoencoders

Activation verbalizers translate the internal representations of large language models into human-readable text. The recently proposed natural language autoencoders (NLAs) learn this by reconstructing...

llms reinforcement-learning fine-tuning benchmarks

arXiv AI

Jun 9

Lost in the Flow with Code Talkers: Unveiling the Instruction-Tuning Tax of Large Language Models in Code Tasks

arXiv:2606. 08676v1 Announce Type: cross Abstract: AI coding assistants have significantly improved developer productivity by automatically suggesting code that aligns with user intent, and many of these tools are now integrated directly into Integrated Development Environments (IDEs).

By Shi Ying Chang, Chiok Yew Ho, Yichen Li, Yintong Huo

llms fine-tuning

arXiv AI

Jun 16

Is Code Better Than Language for Algorithmic Reasoning

arXiv:2606. 15589v1 Announce Type: cross Abstract: For tool-augmented language models, comparing natural-language reasoning with code-execution pipelines is difficult because the comparison changes both the intermediate representation and the execution mechanism.

By Terry Tong, Yu Feng, Surbhi Goel, Dan Roth

llms benchmarks

Related stories