REVIEW 10 cited by
Hypothetical Minds: Scaffolding Theory of Mind for Multi-Agent Tasks with Large Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Multi-agent reinforcement learning (MARL) methods struggle with the non-stationarity of multi-agent systems and fail to adaptively learn online when tested with novel agents. Here, we leverage large language models (LLMs) to create an autonomous agent that can handle these challenges. Our agent, Hypothetical Minds, consists of a cognitively-inspired architecture, featuring modular components for perception, memory, and hierarchical planning over two levels of abstraction. We introduce the Theory of Mind module that scaffolds the high-level planning process by generating hypotheses about other agents' strategies in natural language. It then evaluates and iteratively refines these hypotheses by reinforcing hypotheses that make correct predictions about the other agents' behavior. Hypothetical Minds significantly improves performance over previous LLM-agent and RL baselines on a range of competitive, mixed motive, and collaborative domains in the Melting Pot benchmark, including both dyadic and population-based environments. Additionally, comparisons against LLM-agent baselines and ablations reveal the importance of hypothesis evaluation and refinement for succeeding on complex scenarios.
Forward citations
Cited by 10 Pith papers
-
Language-Informed Synthesis of Rational Agent Models for Grounded Theory-of-Mind Reasoning On-The-Fly
LIRAS synthesizes PDDL world models and agent configurations from language, parses video frames into symbolic states, and runs Bayesian inverse planning (SIAM) to produce human-like graded social inferences across fiv...
-
ToMATO: Verbalizing the Mental States of Role-Playing LLMs for Benchmarking Theory of Mind
ToMATO is a new Theory of Mind benchmark built from AI-generated conversations, covering five mental states, false beliefs, and personality traits, and it shows current LLMs still fall short of human-level social reasoning.
-
Inverse Theory of Mind Modeling for Content Recommendation: From Web Browsing to Dynamic Intelligent Interfaces
A five-stage LLM pipeline infers explainable beliefs and personas from browsing traces, and these inferred profiles match or beat interview-derived profiles on several downstream prediction tasks.
-
Validating Generative Agent-Based Models of Social Norm Enforcement: From Replication to Novel Predictions
Language model agents with personality and theory-of-mind prompts reproduce human third-party punishment and gossip effects, and predict lower anonymous punishment and higher cooperation after group discussion.
-
Understanding Human Limits in Pattern Recognition: A Computational Model of Sequential Reasoning in Rock, Paper, Scissors
An LLM agent reproduces human rock-paper-scissors pattern learning, and interventions suggest that hypothesis generation, not evaluation, is the main cognitive bottleneck.
-
Modeling Open-World Cognition as On-Demand Synthesis of Probabilistic Models
A hybrid language-model and probabilistic-program architecture predicts human judgments on novel open-world reasoning vignettes better than language-model-only baselines.
-
A Framework for Analyzing Abnormal Emergence in Service Ecosystems Through LLM-based Agent Intention Mining
EAMI extracts agent intentions from LLM thought traces, clusters them by meaning, and builds temporal diagrams that trace how new intentions spread through a simulated ecosystem.
-
Reasoning and Behavioral Equilibria in LLM-Nash Games: From Mindsets to Actions
The paper proposes LLM-Nash games, an equilibrium over reasoning prompts that induce action distributions, and argues via a rock-paper-scissors example that such equilibria can differ from classical Nash outcomes.
-
Meta-Thinking in LLMs via Multi-Agent Reinforcement Learning: A Survey
The paper surveys existing work on LLM meta-thinking and argues that multi-agent reinforcement learning is a promising missing ingredient for building self-correcting language models.
-
Large language models for artificial general intelligence (AGI): A survey of foundational principles and approaches
This survey argues that embodiment, symbol grounding, causality, and memory are the foundational principles needed to make large language models achieve artificial general intelligence.
Discussion (0). Continue with ORCID to comment.