Picture for Jakob Foerster

Jakob Foerster

The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind

Add code
Jun 25, 2025
Viaarxiv icon

Programming by Backprop: LLMs Acquire Reusable Algorithmic Abstractions During Code Training

Add code
Jun 23, 2025
Viaarxiv icon

The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

Add code
Apr 10, 2025
Viaarxiv icon

Meta-learning characteristics and dynamics of quantum systems

Add code
Mar 13, 2025
Viaarxiv icon

MLGym: A New Framework and Benchmark for Advancing AI Research Agents

Add code
Feb 20, 2025
Figure 1 for MLGym: A New Framework and Benchmark for Advancing AI Research Agents
Figure 2 for MLGym: A New Framework and Benchmark for Advancing AI Research Agents
Figure 3 for MLGym: A New Framework and Benchmark for Advancing AI Research Agents
Figure 4 for MLGym: A New Framework and Benchmark for Advancing AI Research Agents
Viaarxiv icon

Learning to Reason at the Frontier of Learnability

Add code
Feb 19, 2025
Viaarxiv icon

Multi-Agent Risks from Advanced AI

Add code
Feb 19, 2025
Viaarxiv icon

LOB-Bench: Benchmarking Generative AI for Finance - an Application to Limit Order Book Data

Add code
Feb 13, 2025
Viaarxiv icon

Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps

Add code
Dec 22, 2024
Viaarxiv icon

The Complexity Dynamics of Grokking

Add code
Dec 13, 2024
Viaarxiv icon