Agentic Horizons cover art

All Episodes

Agentic Horizons — 106 episodes

#
Title
1

AI Storytelling with DOME

2

Intelligence Explosion Microeconomics

3

Metacognitive Monitoring: A Human Ability Beyond AI

4

Building Living Software Systems with Generative & Agentic AI

5

Theory of Mind in LLMs

6

Designing AI Personalities

7

FISHNET: Financial Intelligence from Sub-querying, Harmonizing, Neural-Conditioning, Expert Swarms, and Task Planning

8

LLMs Know More Than They Show

9

PDL: A Declarative Prompt Programming Language

10

AI Self-Evolution Using Long Term Memory

11

Responsibility in a Multi-Value Strategic Setting

12

API-Based Web Agents

13

GUS-Net: Social Bias Classification with Generalizations, Unfairness, and Stereotypes

14

Google DeedMind's Talker-Reasoner Architecture

15

A Framework for Representing Knowledge

16

RAG-ConfusionQA: A Benchmark for Evaluating LLMs on Confusing Questions

17

Do LLMs Estimate Uncertainty Well?

18

Stars, Stripes, and Silicon: Unravelling ChatGPT’s Bias

19

Debug Smarter, Not Harder: AI Agents for Error Resolution in Computational Notebooks

20

Interpretable End-to-end Neurosymbolic Reinforcement Learning Agents

21

Situations, Actions, and Causal Laws

22

Programs with Common Sense

23

A Simulation System Towards Solving Societal-Scale Manipulation

24

Good Parenting is All You Need

25

On Computable Numbers, with an Application to the Entscheidungsproblem

26

A Path Towards Autonomous Machine Intelligence

27

The Dartmouth Summer Research Project on Artificial Intelligence

28

Stanford University's One Hundred Year Study on Artificial Intelligence

29

Computing Machinery and Intelligence

30

Steps Toward Artificial Intelligence

31

Building Machines That Learn and Think Like People

32

Alloy Design with Graph Neural Network-Powered LLM-Driven Multi-Agent Systems

33

SchizophreniaInfoBot and the Critical Analysis Filter

34

Diversity of Thought Elicits Stronger Reasoning Capabilities in Multi-Agent Debate Frameworks

35

SynapticRAG: Temporal Dynamic Memory

36

AgentRefine: Enhancing Agent Generalization Through Refinement Tuning

37

Why Agents Are Stupid & What We Can Do About It

38

Towards Efficient AI Policymaking in Economic Simulations

39

Unlocking Abstract Reasoning: How AI Solves Complex Puzzles with Offline Reinforcement Learning

40

CORY: Cooperative Agents for Smarter AI Fine-Tuning

41

SecurityBot: Mentoring LLM with RL Agents to Master Cybersecurity Games

42

AI Consciousness and Global Workspace Theory

43

MAGIS: Multi-Agent Framework for GitHub Issue ReSolution

44

Hierarchical Cooperation Graph Learning

45

Prioritized Heterogeneous League Reinforcement Learning

46

Knowledge Boundary and Persona Dynamic Shape A Better Social Media Agent

47

ITCMA: Computational Consciousness

48

VIRSCI: A Multi-Agent System for Collaborative Scientific Discovery

49

Collaborative Capabilities of Language Models in Blocks World

50

Agent-as-a-Judge: Evaluate Agents with Agents

51

Mentigo: An Intelligent Agent for Mentoring Students in Creative Problem Solving

52

Symbolic and Connectionist AI in Autonomous Agents

53

AgentStudio: A Toolkit for Building General Virtual Agents

54

FairMindSim: Alignment of Behavior, Emotion, and Belief Amid Ethical Dilemmas

55

Machines of Loving Grace

56

GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in LLMs

57

MegaAgent: Autonomous Cooperation in Large-Scale LLM Agent Systems

58

GEM-RAG: Mimicking Human Memory Processes

59

Alignment Faking in Large Language Models

60

DialSim: A New Approach to Evaluating Conversational AI

61

LogicGame: Benchmarking Rule-Based Reasoning Abilities of LLMs

62

AIOS: An Intelligent Agent Operating System

63

Automating Insights: The Future of Data Storytelling with LLMs

64

Socially-Minded Intelligence

65

WebPilot: Mastering Complex Web Tasks

66

Graph of Thoughts

67

AgentGen: Automating Environment and Task Generation for Smarter AI Agents

68

Agent-Based Modeling to Predict the Impact of Generative AI

69

Reflective Monte Carlo Tree Search (R-MCTS)

70

MLE-Bench: Evaluating AI Agents in Real-World Machine Learning Challenges

71

Episodic Future Thinking

72

EgoSocialArena: Measuring Theory of Mind and Socialization

73

Conversate: Job Interview Preparation through Simulations and Feedback

74

Efficient Literature Review Filtration

75

AI-Press: Multi-Agent News Generation and Feedback Simulation

76

Agent S: Using Computers Like Humans

77

HyperAgent: Generalist Software Engineering Agents

78

The Rise and Potential of LLM Based Agents: A Survey

79

Situational Awareness: The Decade Ahead

80

Retrieval Augmented Generation (RAG) and Beyond

81

Improving Factuality and Reasoning through Multiagent Debate

82

Multiagent Requirements Elicitation and Analysis

83

Generative Agents: Interactive Simulacra of Human Behavior

84

The Art of Storytelling: Dynamic Multimodal Narratives

85

Tree of Thoughts

86

PairCoder

87

AI Morality

88

Plurals: Simulated Social Ensembles

89

LLM Persuasion Games

90

Cooperative Resilience in Multi-Agent Systems

91

Human-Like Memory Systems

92

Ex3: Automatic Novel Writing

93

Mental Models in Adaptive Dialog Agents

94

Evolutionary Game Theory Analysis of Human-AI Populations

95

Democracy Research with Generative Agents

96

RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

97

Spontaneous Cooperation of Competing Agents

98

Agent-E: Autonomous Web Navigation

99

Strategist: Learning Strategy with Bi-Level Tree Search

100

The AI Scientist: Automated Discovery

101

AutoGen: A Multi-Agent Framework

102

Project Archetypes for Cognitive Computing Projects

103

ArguMentor: The Value of Counter-Perspectives

104

Thought of Search

105

LLM-Based Agents for Software Engineering: A Survey

106

Reasoning via Planning (RAP)