15 papers
Test-time Offline Reinforcement Learning on Goal-related Experience
Marco Bagatella, Mert Albaba, Jonas Hübotter +2
Foundation models compress a large amount of information in a single, large neural network, which can then be queried for individual tasks. There are strong parallels between this…
Majority Voting for Code Generation
Tim Launer, Jonas Hübotter, Marco Bagatella +2
We investigate Functional Majority Voting (FMV), a method based on functional consensus for code generation with Large Language Models, which identifies a representative solution f…
Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data
Emre Can Acikgoz, Cheng Qian, Jonas Hübotter +3
Large language models (LLMs) are becoming the foundation for autonomous agents that can use tools to solve complex tasks. Reinforcement learning (RL) has emerged as a common approa…
Aligning Language Models from User Interactions
Thomas Kleine Buening, Jonas Hübotter, Barna Pásztor +3
Multi-turn user interactions are among the most abundant data produced by language models, yet we lack effective methods to learn from them. While typically discarded, these intera…
Specialization after Generalization: Towards Understanding Test-Time Training in Foundation Models
Jonas Hübotter, Patrik Wolf, Alexander Shevchenko +3
Recent empirical studies have explored the idea of continuing to train a model at test-time for a given task, known as test-time training (TTT), and have found it to yield signific…
Self-Distillation Enables Continual Learning
Idan Shenfeld, Mehul Damani, Jonas Hübotter +2
Continual learning, enabling models to acquire new skills and knowledge without degrading existing capabilities, remains a fundamental challenge for foundation models. While on-pol…