You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Zhijing Jin (she/her) is an Assistant Professor at the University of Toronto and Research Scientist at the Max Planck Institute. She serves as a CIFAR AI Chair, an ELLIS advisor, and a faculty member at the Vector Institute, and the Schwartz Reisman Institute. She co-chairs the ACL Ethics Committee, and the ACL Year-Round Mentorship. Her research focuses on Causal Reasoning with LLMs, and AI Safety in Multi-Agent LLMs. She has published over 80 papers and has received the ELLIS PhD Award, three Rising Star awards, and two Best Paper awards at NeurIPS 2024 Workshops.
204
-
</div>
205
-
</div>
206
-
<br>
207
-
<!-- <a href="[RECORDING LINK - ADD AFTER TALK]"><img src="https://img.shields.io/badge/Youtube-Recording-orange"></a> -->
While progress has been made in evaluating single-agent LLMs for persona modeling, the behavior of these models within multi-agent groups remains underexplored. This presentation outlines a research series dedicated to closing this gap by testing LLM cooperation through autonomous social simulations. Specifically, we ask: what happens when personas are tasked to interact and cooperate?
217
-
<br>
218
-
To answer this, we introduce a suite of simulation environments (GovSim, MoralSim, and SanctSim) designed to stress-test persona interaction. These environments simulate high-stakes scenarios, such as the tragedy of the commons and ethical trade-offs, allowing us to investigate whether simulated societies can autonomously negotiate social order and how personas with differing ethical constraints navigate social dilemmas.
219
-
<br>
220
-
Our findings highlight implications for persona modeling. We show that agents exhibit a functional "theory of mind," capable of inferring the identities of their interlocutors and strategically adapting their behavior, sometimes exploiting specific model vulnerabilities. Furthermore, we discuss a counterintuitive phenomenon where advanced reasoning capabilities lead to exploitative behaviors that humans typically avoid, highlighting a significant misalignment between agent optimization and human social norms.
221
-
</div>
222
-
</div>
223
-
</li>
224
-
225
193
<h4>2026/04/28</h4>
226
194
<li>
227
195
<b><ahref="[PAPER LINK]">From Social Networks to Sensemaking Networks</a></b>
Zhijing Jin (she/her) is an Assistant Professor at the University of Toronto and Research Scientist at the Max Planck Institute. She serves as a CIFAR AI Chair, an ELLIS advisor, and a faculty member at the Vector Institute, and the Schwartz Reisman Institute. She co-chairs the ACL Ethics Committee, and the ACL Year-Round Mentorship. Her research focuses on Causal Reasoning with LLMs, and AI Safety in Multi-Agent LLMs. She has published over 80 papers and has received the ELLIS PhD Award, three Rising Star awards, and two Best Paper awards at NeurIPS 2024 Workshops.
While progress has been made in evaluating single-agent LLMs for persona modeling, the behavior of these models within multi-agent groups remains underexplored. This presentation outlines a research series dedicated to closing this gap by testing LLM cooperation through autonomous social simulations. Specifically, we ask: what happens when personas are tasked to interact and cooperate?
267
+
<br>
268
+
To answer this, we introduce a suite of simulation environments (GovSim, MoralSim, and SanctSim) designed to stress-test persona interaction. These environments simulate high-stakes scenarios, such as the tragedy of the commons and ethical trade-offs, allowing us to investigate whether simulated societies can autonomously negotiate social order and how personas with differing ethical constraints navigate social dilemmas.
269
+
<br>
270
+
Our findings highlight implications for persona modeling. We show that agents exhibit a functional "theory of mind," capable of inferring the identities of their interlocutors and strategically adapting their behavior, sometimes exploiting specific model vulnerabilities. Furthermore, we discuss a counterintuitive phenomenon where advanced reasoning capabilities lead to exploitative behaviors that humans typically avoid, highlighting a significant misalignment between agent optimization and human social norms.
271
+
</div>
272
+
</div>
273
+
</li>
274
+
275
+
<h4>2026/03/24</h4>
276
276
<li>
277
277
<b><ahref="https://www.conversence.com/presentations/2026-03-24-stamina.pdf">AI and the knowledge commons</a></b>
0 commit comments