Sotabase

Career

· Ph.D. Student in EECS, UC Berkeley2024–

Publications (11)

Multi-Agent Risks from Advanced AI
arXiv.org · 2025
88
cited
Welfare Diplomacy: Benchmarking Language Model Cooperation
arXiv.org · 2023
39
cited
SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
arXiv.org · 2025
25
cited
Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning
Neural Information Processing Systems · 2024
15
cited
Who Needs to Know? Minimal Knowledge for Optimal Coordination
International Conference on Machine Learning · 2023
8
cited
Learning Deterministic Finite Automata Decompositions from Examples and Demonstrations
Formal Methods in Computer-Aided Design · 2022
7
cited
Automata Conditioned Reinforcement Learning with Experience Replay
5
cited
Learning Symbolic Task Decompositions for Multi-Agent Teams
Adaptive Agents and Multi-Agent Systems · 2025
5
cited
Provably Correct Automata Embeddings for Optimal Automata-Conditioned Reinforcement Learning
NeuS · 2025
3
cited
Robust and Diverse Multi-Agent Learning via Rational Policy Gradient
arXiv.org · 2025
1
cited
Imitation Learning for Multi-turn LM Agents via On-policy Expert Corrections
arXiv.org · 2025
Sotabase
Niklas Lauffer | Researcher Profile | Sotabase | Sotabase