28 citations · 113 across the 33 of their papers we have counts for
37 papers
From Solo to Social Learning: Characterizing Recursive Social Improvement in LLMs
Kunal Jha, Max Kleiman-Weiner, Natasha Jaques
Large language models (LLMs) can now improve themselves by revising the instructions they follow, and LLM agents are increasingly orchestrated to work together on complex problems.…
CogGym: Towards Large-Scale Comparative Evaluation of Human and Machine Cognition
Lance Ying, Jinzhou Wu, Yingshan Susan Wang +53
Understanding and modeling human intelligence are parallel goals shared by artificial intelligence (AI) and cognitive science. As AI systems grow increasingly capable, in what ways…
Tapes Together Strong: The Co-evolution of Computation and Cooperation
Kunal Jha, Francesco Cicala, Blaise Agüera y Arcas +4
How does cooperation evolve in complex agentic systems? Prior work in evolutionary game theory studies why individuals are incentivized to cooperate by isolating social interaction…
Evaluating Rational Contracting in Natural Language
Bhavyesh Sajja, Max Kleiman-Weiner, Roger Zimmermann +1
The emergence of language-based AI agents promises to transform the scope of machine economic activity. Instead of just proposing bids or following hard-coded protocols, such agent…
Commitment To Cooperation With Self-Negotiated Contracts
Tim Wyse, Kaitlin Bustos, Yulia Volkova +1
As AI agents operate with increasing autonomy in a multi-agent world, they will need to learn to cooperate with other agents and with humans to generate mutual benefits. However, c…
AI Assistants Overassist
Verona Teo, Raghav Jain, Tobias Gerstenberg +1
Large language models (LLMs) are increasingly used as tutors and thought partners, helping users reason through problems. While guidance from AI assistants can scaffold thinking an…
A Model of Multi-turn Human Persuadability Using Probabilistic Belief Tracing
Jared Moore, Noah Goodman, Nick Haber +1
Large language models can shift human beliefs across high-stakes domains, but most persuasion studies rely on pre/post belief change. These endpoint measures identify whether persu…
Task diversity produces systematic transfer but inhibits continual reinforcement learning
Purab Seth, Neil Shah, Ishaan Sinha +4
Continual reinforcement learning (RL) aims to produce agents that never stop adapting to new tasks. A key question is how this interacts with the diversity of tasks an agent experi…
Boundedly Rational Meta-Learning in Sequential Consumer Choice
Mehrzad Khosravi, Max Kleiman-Weiner, Hema Yoganarasimhan
Many consumer decisions involve repeated choices under uncertainty, where experience in one context may inform decisions in another. For example, experience with a brand in one mar…
How LLMs Distort Our Written Language
Marwa Abdulhai, Isadora White, Yanming Wan +4
Large language models (LLMs) are used by over a billion people globally, most often to assist with writing. In this work, we demonstrate that LLMs not only alter the voice and tone…
Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians
Kartik Chandra, Max Kleiman-Weiner, Jonathan Ragan-Kelley +1
"AI psychosis" or "delusional spiraling" is an emerging phenomenon where AI chatbot users find themselves dangerously confident in outlandish beliefs after extended chatbot convers…
Evaluating LLMs in Open-Source Games
Swadesh Sistla, Max Kleiman-Weiner
Large Language Models' (LLMs) programming capabilities enable their participation in open-source games: a game-theoretic setting in which players submit computer programs in lieu o…
Cognitive Foundations for Reasoning and Their Manifestation in LLMs
Priyanka Kargupta, Shuyue Stella Li, Haocheng Wang +9
Large language models (LLMs) solve complex problems yet fail on simpler variants, suggesting they achieve correct outputs through mechanisms fundamentally different from human reas…
When Assisting One Disempowers Another
Claire Yang, Claire Jie Zhang, Maya Cakmak +1
Personal AI agents are increasingly deployed in shared environments, where their actions affect not just the primary user they are assisting, but bystanders who never consented to…
Modeling Others' Minds as Code
Kunal Jha, Aydan Yuenan Huang, Eric Ye +2
Accurate prediction of human behavior is essential for robust and safe human-AI collaboration. However, existing approaches for modeling people are often data-hungry and brittle be…
Generative Value Conflicts Reveal LLM Priorities
Andy Liu, Kshitish Ghate, Mona Diab +3
Past work seeks to align large language model (LLM)-based assistants with a target set of values, but such assistants are frequently forced to make tradeoffs between values when de…
Estimating the Empowerment of Language Model Agents
Jinyeop Song, Jeff Gore, Max Kleiman-Weiner
As language model (LM) agents become increasingly capable and adopted in real-world applications, there is a growing need for scalable evaluation frameworks beyond costly, manually…
Preserving Sense of Agency: User Preferences for Robot Autonomy and User Control across Household Tasks
Claire Yang, Heer Patel, Max Kleiman-Weiner +1
Roboticists often design with the assumption that assistive robots should be fully autonomous. However, it remains unclear whether users prefer highly autonomous robots, as prior w…
The Lock-in Hypothesis: Stagnation by Algorithm
Tianyi Alex Qiu, Zhonghao He, Tejasveer Chugh +1
The training and deployment of large language models (LLMs) create a feedback loop with human users: models learn human beliefs from data, reinforce these beliefs with generated co…
Are Language Models Consequentialist or Deontological Moral Reasoners?
Keenan Samway, Max Kleiman-Weiner, David Guzman Piedrahita +3
As AI systems increasingly navigate applications in healthcare, law, and governance, understanding how they handle ethically complex scenarios becomes critical. Previous work has m…
Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination
Kunal Jha, Wilka Carvalho, Yancheng Liang +3
Zero-shot coordination (ZSC), the ability to adapt to a new partner in a cooperative task, is a critical component of human-compatible AI. While prior work has focused on training…
SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior
Jing-Jing Li, Valentina Pyatkin, Max Kleiman-Weiner +7
The ideal AI safety moderation system would be both structurally interpretable (so its decisions can be reliably explained) and steerable (to align to safety standards and reflect…
Value Internalization: Learning and Generalizing from Social Reward
Frieda Rong, Max Kleiman-Weiner
Social rewards shape human behavior. During development, a caregiver guides a learner's behavior towards culturally aligned goals and values. How do these behaviors persist and gen…
Language Model Alignment in Multilingual Trolley Problems
Zhijing Jin, Max Kleiman-Weiner, Giorgio Piatti +9
We evaluate the moral alignment of LLMs with human preferences in multilingual trolley problems. Building on the Moral Machine experiment, which captures over 40 million human judg…