AIConfPaper
← Search

Sneheel Sarangi

5 accepted papers

2026

Position: Time to Close The Validation Gap in LLM Social Simulations

Maximilian Puelma Touzel, Sneheel Sarangi, Aurélien Bück-Kaeffer, Zachary Yang, Jean-François Godbout, Reihaneh Rabbany
ICML 2026poster

LLM-based social simulations—in which many language model agents interact over multiple turns—are rapidly proliferating across policy analysis, epidemiology, and computational social science. Yet the field lacks consensus on how to validate these simulations, with evaluation methods that are sparse,…

Cited by 0Source ↗Scholar ↗
2025

Agentic-ToM: Cognition-Inspired Agentic Processing For Enhancing Theory of Mind Reasoning

Sneheel Sarangi, Chetan Talele, Hanan Salam
EMNLP 2025

The capacity to attribute mental states like beliefs, desires, and intentions to oneself and others, known as Theory of Mind (ToM), is fundamental to human social intelligence. As Large Language Models (LLMs) are increasingly integrated into complex interactive systems, developing their ToM capabili

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Decompose-ToM: Enhancing Theory of Mind Reasoning in Large Language Models through Simulation and Task Decomposition

Sneheel Sarangi, Maha Elgarf, Hanan Salam
COLING 2025main

Theory of Mind (ToM) is the ability to understand and reflect on the mental states of others. Although this capability is crucial for human interaction, testing on Large Language Models (LLMs) reveals that they possess only a rudimentary understanding of it. Although the most capable closed-source L…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2025

Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia

Chandler Smith, Marwa Abdulhai, Manfred Diaz, Marko Tesic, Rakshit Trivedi, Sasha Vezhnevets +80
NeurIPS 2025poster

Large Language Model (LLM) agents have demonstrated impressive capabilities for social interaction and are increasingly being deployed in situations where they might engage with both human and artificial agents. These interactions represent a critical frontier for LLM-based agents, yet existing eval…

Cited by 0Source ↗Scholar ↗
2025

SandboxSocial: A Sandbox for Social Media Using Multimodal AI Agents

Maximilian Puelma Touzel, Sneheel Sarangi, Gayatri Krishnakumar, Busra Tugce Gurbuz, Austin Welch, Zachary Yang +9
IJCAI 2025

The online information ecosystem enables influence campaigns of unprecedented scale and impact. We urgently need empirically grounded approaches to counter the growing threat of malicious campaigns, now amplified by generative AI. But, developing defenses in real-world settings is impractical. Socia

Cited by 0Source ↗PDF ↗code ↗Scholar ↗