Skip to content

Commit d0e011d

Browse files
authored
Update index.html
1 parent 26b1f50 commit d0e011d

1 file changed

Lines changed: 33 additions & 33 deletions

File tree

stamina/index.html

Lines changed: 33 additions & 33 deletions
Original file line numberDiff line numberDiff line change
@@ -190,38 +190,6 @@ <h4>[DATE Y/M/D]</h4>
190190

191191
<br>
192192

193-
<h4>2026/04/14</h4>
194-
<li>
195-
<b><a href="[PAPER LINK]">Testing and Improving Multi-Agent LLM Cooperation</a></b>
196-
<br>
197-
Presenter: <u><a href="https://zhijing-jin.com/" target="_blank" rel="noopener noreferrer">Zhijing Jin</a></u>, University of Toronto
198-
<a class="btn btn-info btn-xs" data-toggle="collapse" href="#20260414-bio" role="button" aria-expanded="false">
199-
Speaker Bio
200-
</a>
201-
<div class="collapse" id="20260414-bio">
202-
<div class="card card-body">
203-
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> -->
208-
<!-- <a href="[PAPERLINK]"><img src="https://img.shields.io/badge/Paper-link-important"></a> -->
209-
<!-- <a href="[GITHUB_LINK]"><img src="https://img.shields.io/badge/Github-link-lightgrey"></a> -->
210-
<!-- <a href="[SLIDES_LINK]"><img src="https://img.shields.io/badge/Talk-Slides-blue"></a> -->
211-
<a class="btn btn-primary btn-xs" data-toggle="collapse" href="#20260414-abstract" role="button" aria-expanded="false">
212-
Abstract
213-
</a>
214-
<div class="collapse" id="20260414-abstract">
215-
<div class="card card-body">
216-
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-
225193
<h4>2026/04/28</h4>
226194
<li>
227195
<b><a href="[PAPER LINK]">From Social Networks to Sensemaking Networks</a></b>
@@ -272,7 +240,39 @@ <h3 style="text-align:center">Past Talks (<a href="https://www.youtube.com/@Comp
272240

273241
<h4 style="text-align:center; margin-top:30px;">Spring 2026</h4>
274242

275-
<h4>2026/03/24</h4>
243+
<h4>2026/04/14</h4>
244+
<li>
245+
<b><a href="[PAPER LINK]">Testing and Improving Multi-Agent LLM Cooperation</a></b>
246+
<br>
247+
Presenter: <u><a href="https://zhijing-jin.com/" target="_blank" rel="noopener noreferrer">Zhijing Jin</a></u>, University of Toronto
248+
<a class="btn btn-info btn-xs" data-toggle="collapse" href="#20260414-bio" role="button" aria-expanded="false">
249+
Speaker Bio
250+
</a>
251+
<div class="collapse" id="20260414-bio">
252+
<div class="card card-body">
253+
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.
254+
</div>
255+
</div>
256+
<br>
257+
<a href="https://www.youtube.com/watch?v=Bme6Q8nKfrs"><img src="https://img.shields.io/badge/Youtube-Recording-orange"></a>
258+
<!-- <a href="[PAPERLINK]"><img src="https://img.shields.io/badge/Paper-link-important"></a> -->
259+
<!-- <a href="[GITHUB_LINK]"><img src="https://img.shields.io/badge/Github-link-lightgrey"></a> -->
260+
<!-- <a href="[SLIDES_LINK]"><img src="https://img.shields.io/badge/Talk-Slides-blue"></a> -->
261+
<a class="btn btn-primary btn-xs" data-toggle="collapse" href="#20260414-abstract" role="button" aria-expanded="false">
262+
Abstract
263+
</a>
264+
<div class="collapse" id="20260414-abstract">
265+
<div class="card card-body">
266+
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>
276276
<li>
277277
<b><a href="https://www.conversence.com/presentations/2026-03-24-stamina.pdf">AI and the knowledge commons</a></b>
278278
<br>

0 commit comments

Comments
 (0)