News
News & updates.
Grants, press, talks, and milestone publications from the lab.
-
Prof. Heydari joined the Network Science Institute as Core Faculty.
Babak Heydari has joined Northeastern's Network Science Institute as Core Faculty, deepening the lab's ties to the broader NSI community.
-
Prof. Heydari promoted to Full Professor.
Babak Heydari has been promoted to Professor in the Mechanical & Industrial Engineering Department at Northeastern University's College of Engineering.
-
New publication in the Journal of Mechanical Design: "Architecting adaptive networks."
Q. Chen and B. Heydari publish in the Journal of Mechanical Design (148(1): 011701) — reinforcement learning with generative policies for multi-agent governance.
-
New paper accepted at the Journal of Mechanical Design: "Adaptive Information Modulation."
Q. Chen, S. Ilami, N. Lorè, and B. Heydari design governance mechanisms for multi-agent AI systems — accepted to the Journal of Mechanical Design.
-
New preprint: "Communication Enhances LLMs' Stability in Strategic Thinking."
N. Lorè and B. Heydari show how communication channels stabilize the strategic behavior of large language models.
-
New preprint: "The Architecture of Illusion: Network Opacity and Strategic Escalation."
R. Ebrahimi, S. Ilami, B. Heydari, I. Trevino, and M. Franceschetti examine how opaque network structure drives strategic escalation.
-
New working paper: "Cognitive Heuristics are Necessary for Human-Like Multi-Agent Dynamics in LLMs."
H. Zhu and B. Heydari argue that adding cognitive heuristics to LLM agents is what makes their multi-agent behavior look human-like.
-
New publication in the Strategic Management Journal.
Where to allocate heterogeneous inventors in a firm's internal innovation network — and how that allocation interacts with landscape complexity — appears in SMJ.
-
Our work on the strategic behavior of LLM agents is covered by Scientific American.
Scientific American featured the lab's research on how large language models behave as strategic agents — when they reason about game structure, when they're swayed by framing, and what that means for deploying AI in social settings.
-
$1M NSF IHBEM grant on integrating group-level human behavior into epidemic modeling.
A new NSF IHBEM award supports work on bringing group-level human behavior — beyond simple individual choice — into the inner loop of epidemic models.
-
New publication in Nature Scientific Reports: "Strategic Behavior of Large Language Models."
A systematic study of how GPT-3.5, GPT-4, and LLaMa-2 play four canonical two-player games across five contextual framings — and what their behavior says about deploying LLMs as strategic agents.
More news and full publications will be added later.