Agentic Complex Systems

Journal Club

Every week, we choose one paper (or a paper idea) as a starting point for discussion and idea generation.

August 2025

  • August 05, 2025, Playing repeated games with large language models, paper link
  • August 12, 2025, Moral Foundations of Large Language Models, paper link
  • August 19, 2025, Building and evaluating alignment auditing agents, paper link

September 2025

  • September 02, 2025, Spin glass model of in-context learning, paper link
  • September 23, 2025, Why Language Models Hallucinate, paper link
  • September 30, 2025, AI Agents can Coordinate Beyond Human Scale, paper link

October 2025

  • October 07, 2025, The Virtual Lab of AI agents designs new SARS-CoV-2 nanobodies, paper link
  • October 21, 2025, The Curious Case of Curiosity across Human Cultures and LLMs, paper link

November 2025

  • November 04, 2025, Language Models are Injective and hence Invertible, paper link
  • November 11, 2025, On the Representational Capacity of Neural Language Models with Chain of Thought Reasoning, paper link

December 2025

  • December 02, 2025, Mercury: Ultra-Fast Language Models Based on Diffusion, paper link

February 2026

  • February 03, 2026, Emergent Misalignment (article set), link 1 | link 2 | link 3
  • February 27, 2026, Are Aligned Large Language Models Still Misaligned?, paper link

March 2026

  • March 06, 2026, Emergently Misaligned Language Models Show Behavioral Self-Awareness That Shifts With Subsequent Realignment, paper link
  • March 13, 2026, Discovering Implicit Large Language Model Alignment Objectives, paper link
  • March 27, 2026, Toward universal steering and monitoring of AI models, paper link

April 2026

  • April 10, 2026, Towards end-to-end automation of AI research, paper link
  • April 17, 2026, Neural Computers, paper link

May 2026

  • May 08, 2026, Emotion Concepts and their Function in a Large Language Model, paper link
  • May 15, 2026, Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior, paper link
  • May 22, 2026, Spontaneous symmetry breaking and Goldstone modes for deep information propagation, paper link
  • May 29, 2026, KAN for Language Models, presentation link

June 2026

  • June 12, 2026, Problem-Induced Topologies for Multi-Agent LLM Systems: Conjectures
  • June 19, 2026, AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation, paper link
  • June 26, 2026, Reproducing Computational Neuroscience With Agents: Rebuilding the Models Behind the Theories, presentation link

July 2026

  • July 03, 2026, Goedel-Architect: Streamlining Formal Theorem Proving with Blueprint Generation and Refinement, paper link
  • July 17, 2026, LLMs as Noisy Channels: A Shannon Perspective on Model Capacity and Scaling Laws, paper link