papers

Publications (18)

cs.CL2025

What Makes Large Language Models Reason in (Multi-Turn) Code Generation?

Kunhao Zheng, Juliette Decugis, Jonas Gehring +3

Prompting techniques such as chain-of-thought have established themselves as a popular vehicle for improving the outputs of large language models (LLMs). For code generation, howev…

cs.CL2025

RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning

Jonas Gehring, Kunhao Zheng, Jade Copet +4

Large language models (LLMs) deployed as agents solve user-specified tasks over multiple steps while keeping the required manual engagement to a minimum. Crucially, such LLMs need…

cs.LG2023

Leveraging Demonstrations with Latent Space Priors

Jonas Gehring, Deepak Gopinath, Jungdam Won +3

Demonstrations provide insight into relevant state or action space regions, bearing great potential to boost the efficiency and practicality of reinforcement learning agents. In th…

cs.AI2017

STARDATA: A StarCraft AI Research Dataset

Zeming Lin, Jonas Gehring, Vasil Khalidov +1

We release a dataset of 65646 StarCraft replays that contains 1535 million frames and 496 million player actions. We provide full game state data along with the original replays th…

cs.LG2026

Towards a Neural Debugger for Python

Maximilian Beck, Jonas Gehring, Jannik Kossen +1

Training large language models (LLMs) on Python execution traces grounds them in code execution and enables the line-by-line execution prediction of whole Python programs, effectiv…

cs.LG2018

High-Level Strategy Selection under Partial Observability in StarCraft: Brood War

Jonas Gehring, Da Ju, Vegard Mella +3

We consider the problem of high-level strategy selection in the adversarial setting of real-time strategy games from a reinforcement learning perspective, where taking an action co…

cs.PL2023

Large Language Models for Compiler Optimization

Chris Cummins, Volker Seeker, Dejan Grubisic +8

We explore the novel application of Large Language Models to code optimization. We present a 7B-parameter transformer model trained from scratch to optimize LLVM assembly for code…

cs.SE2024

The Larger the Better? Improved LLM Code-Generation via Budget Reallocation

Michael Hassid, Tal Remez, Jonas Gehring +2

It is a common belief that large language models (LLMs) are better than smaller-sized ones. However, larger models also require significantly more time and compute during inference…

cs.SE2025

CWM: An Open-Weights LLM for Research on Code Generation with World Models

FAIR CodeGen team, Jade Copet, Quentin Carbonneaux +48

We release Code World Model (CWM), a 32-billion-parameter open-weights LLM, to advance research on code generation with world models. To improve code understanding beyond what can…

cs.SE2026

Toward Training Superintelligent Software Agents through Self-Play SWE-RL

Yuxiang Wei, Zhiqing Sun, Emily McMilin +6

While current software agents powered by large language models (LLMs) and agentic reinforcement learning (RL) can boost programmer productivity, their training data (e.g., GitHub i…

cs.PL2024

Meta Large Language Model Compiler: Foundation Models of Compiler Optimization

Chris Cummins, Volker Seeker, Dejan Grubisic +4

Large Language Models (LLMs) have demonstrated remarkable capabilities across a variety of software engineering and coding tasks. However, their application in the domain of code a…

cs.LG2021

Hierarchical Skills for Efficient Exploration

Jonas Gehring, Gabriel Synnaeve, Andreas Krause +1

In reinforcement learning, pre-trained low-level skills have the potential to greatly facilitate exploration. However, prior knowledge of the downstream task is required to strike…

cs.CL2024

Code Llama: Open Foundation Models for Code

Baptiste Rozière, Jonas Gehring, Fabian Gloeckle +23

We release Code Llama, a family of large language models for code based on Llama 2 providing state-of-the-art performance among open models, infilling capabilities, support for lar…

cs.CL2017

Convolutional Sequence to Sequence Learning

Jonas Gehring, Michael Auli, David Grangier +2

The prevalent approach to sequence to sequence learning maps an input sequence to a variable length output sequence via recurrent neural networks. We introduce an architecture base…

cs.CL2025

The KoLMogorov Test: Compression by Code Generation

Ori Yoran, Kunhao Zheng, Fabian Gloeckle +3

Compression is at the heart of intelligence. A theoretically optimal way to compress any sequence of data is to find the shortest program that outputs that sequence and then halts.…

cs.LG2018

Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger

Gabriel Synnaeve, Zeming Lin, Jonas Gehring +5

We formulate the problem of defogging as state estimation and future state prediction from previous, partial observations in the context of real-time strategy games. We propose to…

cs.CL2017

A Convolutional Encoder Model for Neural Machine Translation

Jonas Gehring, Michael Auli, David Grangier +1

The prevalent approach to neural machine translation relies on bi-directional LSTMs to encode the source sentence. In this paper we present a faster and simpler architecture based…

cs.LG2026

Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL

Kunhao Zheng, Pierre Chambon, Juliette Decugis +4

Linear interpolation between fine-tuned checkpoints has been shown to trace the Pareto front between competing objectives, but whether extrapolative weight averaging can extend suc…