114 citations · 353 across the 89 of their papers we have counts for
24 papers · 1 filter
GitSwarm: Decentralized Compounding Inference
Vedant Shah, Ankur Samanta, Paras Dahal +11
Long-horizon problem solving and scientific research require computation to accumulate across successive attempts. Partial solutions, experimental findings, and unsuccessful approa…
CivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI
Austin Tudor David Andrews, Liam Wilkinson, Jamie Heagerty +3
We present CivBench, an open-source benchmark for evaluating language model agents in long-horizon, tool-mediated environments through the Model Context Protocol (MCP). A single ep…
AI Research Preference Models
Thomas Simon Foster, Bassel Al Omari, Tingchen Fu +30
AI research agents (AIRA) can now carry machine learning experiments from proposal through implementation and evaluation. Yet progress on frontier tasks is throttled by the cost of…
Is Inter-Seed Cross-Play Enough? Evaluating the Robustness of Zero-Shot Coordination Algorithms to Implementation Details
Maksymilian Wolski, Nicholas Hoernle, Johannes Forkel +1
AI agents deployed in real-world settings must be capable of coordinating with humans and other AI agents they have not encountered before. Zero-shot coordination (ZSC) algorithms…
Autodata: An agentic data scientist to create high quality synthetic data
Ilia Kulikov, Chenxi Whitehouse, Tianhao Wu +12
We introduce Autodata, a general method that enables AI agents to act as data scientists who build high quality training and evaluation data. We show how to train (meta-optimize) s…
Towards End-to-End Automation of AI Research
Yutaro Yamada, Robert Tjarko Lange, Cong Lu +5
The automation of science is a long-standing ambition in the field of AI. While the community has made significant progress in automating individual components of the scientific pr…
Recurrent Structural Policy Gradient for Partially Observable Mean Field Games
Clarisse Wibault, Johannes Forkel, Sebastian Towers +9
Mean Field Games (MFGs) provide a principled framework for modelling interactions in large population systems. However, algorithmic progress has been limited since model-free metho…
Asking the Right Questions: Improving Reasoning with Generated Stepping Stones
Hengyuan Hu, Tingchen Fu, Minqi Jiang +3
Recent years have witnessed tremendous progress in enabling LLMs to solve complex reasoning tasks such as math and coding. As we start to apply LLMs to harder tasks that they may n…
The Yokai Learning Environment: Tracking Beliefs Over Space and Time
Constantin Ruhdorfer, Matteo Bortoletto, Johannes Forkel +2
The ability to cooperate with unknown partners is a central challenge in cooperative AI and widely studied in the form of zero-shot coordination (ZSC), which evaluates an algorithm…
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
Yutaro Yamada, Robert Tjarko Lange, Cong Lu +5
AI is increasingly playing a pivotal role in transforming how scientific discoveries are made. We introduce The AI Scientist-v2, an end-to-end agentic system capable of producing t…
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
Chris Lu, Cong Lu, Robert Tjarko Lange +3
One of the grand challenges of artificial general intelligence is developing agents capable of conducting scientific research and discovering new knowledge. While frontier models h…
Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning
Jonathan Cook, Chris Lu, Edward Hughes +2
Cultural accumulation drives the open-ended and diverse progress in capabilities spanning human history. It builds an expanding body of knowledge and skills by combining individual…
Scaling Opponent Shaping to High Dimensional Games
Akbir Khan, Timon Willi, Newton Kwan +5
In multi-agent settings with mixed incentives, methods developed for zero-sum games have been shown to lead to detrimental outcomes. To address this issue, opponent shaping (OS) me…
Learning Multi-Agent Communication with Contrastive Learning
Yat Long Lo, Biswa Sengupta, Jakob Foerster +1
Communication is a powerful tool for coordination in multi-agent RL. But inducing an effective, common language is a difficult challenge, particularly in the decentralized setting.…
Cheap Talk Discovery and Utilization in Multi-Agent Reinforcement Learning
Yat Long Lo, Christian Schroeder de Witt, Samuel Sokota +2
By enabling agents to communicate, recent cooperative multi-agent reinforcement learning (MARL) methods have demonstrated better task performance and more coordinated behavior. Mos…
K-level Reasoning for Zero-Shot Coordination in Hanabi
Brandon Cui, Hengyuan Hu, Luis Pineda +1
The standard problem setting in cooperative multi-agent settings is self-play (SP), where the goal is to train a team of agents that works well together. However, optimal SP polici…
Self-Explaining Deviations for Coordination
Hengyuan Hu, Samuel Sokota, David Wu +4
Fully cooperative, partially observable multi-agent problems are ubiquitous in the real world. In this paper, we focus on a specific subclass of coordination problems in which huma…
Illusory Attacks: Information-Theoretic Detectability Matters in Adversarial Attacks
Tim Franzmeyer, Stephen McAleer, João F. Henriques +4
Autonomous agents deployed in the real world need to be robust against adversarial attacks on sensory inputs. Robustifying agent policies requires anticipating the strongest attack…
Generalized Beliefs for Cooperative AI
Darius Muglich, Luisa Zintgraf, Christian Schroeder de Witt +2
Self-play is a common paradigm for constructing solutions in Markov games that can yield optimal policies in collaborative settings. However, these policies often adopt highly-spec…
Model-Free Opponent Shaping
Chris Lu, Timon Willi, Christian Schroeder de Witt +1
In general-sum games, the interaction of self-interested learning agents commonly leads to collectively worst-case outcomes, such as defect-defect in the iterated prisoner's dilemm…
Communicating via Markov Decision Processes
Samuel Sokota, Christian Schroeder de Witt, Maximilian Igl +6
We consider the problem of communicating exogenous information by means of Markov decision process trajectories. This setting, which we call a Markov coding game (MCG), generalizes…
Centralized Model and Exploration Policy for Multi-Agent RL
Qizhen Zhang, Chris Lu, Animesh Garg +1
Reinforcement learning (RL) in partially observable, fully cooperative multi-agent settings (Dec-POMDPs) can in principle be used to address many real-world challenges such as cont…
A New Formalism, Method and Open Issues for Zero-Shot Coordination
Johannes Treutlein, Michael Dennis, Caspar Oesterheld +1
In many coordination problems, independently reasoning humans are able to discover mutually compatible policies. In contrast, independently trained self-play policies are often mut…
"Other-Play" for Zero-Shot Coordination
Hengyuan Hu, Adam Lerer, Alex Peysakhovich +1
We consider the problem of zero-shot coordination - constructing AI agents that can coordinate with novel partners they have not seen before (e.g. humans). Standard Multi-Agent Rei…