All Episodes
Agentic Horizons — 106 episodes
AI Storytelling with DOME
Intelligence Explosion Microeconomics
Metacognitive Monitoring: A Human Ability Beyond AI
Building Living Software Systems with Generative & Agentic AI
Theory of Mind in LLMs
Designing AI Personalities
FISHNET: Financial Intelligence from Sub-querying, Harmonizing, Neural-Conditioning, Expert Swarms, and Task Planning
LLMs Know More Than They Show
PDL: A Declarative Prompt Programming Language
AI Self-Evolution Using Long Term Memory
Responsibility in a Multi-Value Strategic Setting
API-Based Web Agents
GUS-Net: Social Bias Classification with Generalizations, Unfairness, and Stereotypes
Google DeedMind's Talker-Reasoner Architecture
A Framework for Representing Knowledge
RAG-ConfusionQA: A Benchmark for Evaluating LLMs on Confusing Questions
Do LLMs Estimate Uncertainty Well?
Stars, Stripes, and Silicon: Unravelling ChatGPT’s Bias
Debug Smarter, Not Harder: AI Agents for Error Resolution in Computational Notebooks
Interpretable End-to-end Neurosymbolic Reinforcement Learning Agents
Situations, Actions, and Causal Laws
Programs with Common Sense
A Simulation System Towards Solving Societal-Scale Manipulation
Good Parenting is All You Need
On Computable Numbers, with an Application to the Entscheidungsproblem
A Path Towards Autonomous Machine Intelligence
The Dartmouth Summer Research Project on Artificial Intelligence
Stanford University's One Hundred Year Study on Artificial Intelligence
Computing Machinery and Intelligence
Steps Toward Artificial Intelligence
Building Machines That Learn and Think Like People
Alloy Design with Graph Neural Network-Powered LLM-Driven Multi-Agent Systems
SchizophreniaInfoBot and the Critical Analysis Filter
Diversity of Thought Elicits Stronger Reasoning Capabilities in Multi-Agent Debate Frameworks
SynapticRAG: Temporal Dynamic Memory
AgentRefine: Enhancing Agent Generalization Through Refinement Tuning
Why Agents Are Stupid & What We Can Do About It
Towards Efficient AI Policymaking in Economic Simulations
Unlocking Abstract Reasoning: How AI Solves Complex Puzzles with Offline Reinforcement Learning
CORY: Cooperative Agents for Smarter AI Fine-Tuning
SecurityBot: Mentoring LLM with RL Agents to Master Cybersecurity Games
AI Consciousness and Global Workspace Theory
MAGIS: Multi-Agent Framework for GitHub Issue ReSolution
Hierarchical Cooperation Graph Learning
Prioritized Heterogeneous League Reinforcement Learning
Knowledge Boundary and Persona Dynamic Shape A Better Social Media Agent
ITCMA: Computational Consciousness
VIRSCI: A Multi-Agent System for Collaborative Scientific Discovery
Collaborative Capabilities of Language Models in Blocks World
Agent-as-a-Judge: Evaluate Agents with Agents
Mentigo: An Intelligent Agent for Mentoring Students in Creative Problem Solving
Symbolic and Connectionist AI in Autonomous Agents
AgentStudio: A Toolkit for Building General Virtual Agents
FairMindSim: Alignment of Behavior, Emotion, and Belief Amid Ethical Dilemmas
Machines of Loving Grace
GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in LLMs
MegaAgent: Autonomous Cooperation in Large-Scale LLM Agent Systems
GEM-RAG: Mimicking Human Memory Processes
Alignment Faking in Large Language Models
DialSim: A New Approach to Evaluating Conversational AI
LogicGame: Benchmarking Rule-Based Reasoning Abilities of LLMs
AIOS: An Intelligent Agent Operating System
Automating Insights: The Future of Data Storytelling with LLMs
Socially-Minded Intelligence
WebPilot: Mastering Complex Web Tasks
Graph of Thoughts
AgentGen: Automating Environment and Task Generation for Smarter AI Agents
Agent-Based Modeling to Predict the Impact of Generative AI
Reflective Monte Carlo Tree Search (R-MCTS)
MLE-Bench: Evaluating AI Agents in Real-World Machine Learning Challenges
Episodic Future Thinking
EgoSocialArena: Measuring Theory of Mind and Socialization
Conversate: Job Interview Preparation through Simulations and Feedback
Efficient Literature Review Filtration
AI-Press: Multi-Agent News Generation and Feedback Simulation
Agent S: Using Computers Like Humans
HyperAgent: Generalist Software Engineering Agents
The Rise and Potential of LLM Based Agents: A Survey
Situational Awareness: The Decade Ahead
Retrieval Augmented Generation (RAG) and Beyond
Improving Factuality and Reasoning through Multiagent Debate
Multiagent Requirements Elicitation and Analysis
Generative Agents: Interactive Simulacra of Human Behavior
The Art of Storytelling: Dynamic Multimodal Narratives
Tree of Thoughts
PairCoder
AI Morality
Plurals: Simulated Social Ensembles
LLM Persuasion Games
Cooperative Resilience in Multi-Agent Systems
Human-Like Memory Systems
Ex3: Automatic Novel Writing
Mental Models in Adaptive Dialog Agents
Evolutionary Game Theory Analysis of Human-AI Populations
Democracy Research with Generative Agents
RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
Spontaneous Cooperation of Competing Agents
Agent-E: Autonomous Web Navigation
Strategist: Learning Strategy with Bi-Level Tree Search
The AI Scientist: Automated Discovery
AutoGen: A Multi-Agent Framework
Project Archetypes for Cognitive Computing Projects
ArguMentor: The Value of Counter-Perspectives
Thought of Search
LLM-Based Agents for Software Engineering: A Survey
Reasoning via Planning (RAP)