Enoch H. Kang

Best AI papers explained

Cut through the noise. We curate and break down the most important AI papers so you don’t have to.

Be sure to visit the podcast's website and support the creator: podcasters.spotify.com

Author

Enoch H. Kang

Category

Technology

Podcast website

podcasters.spotify.com

Latest episode

Nov 19, 2026

Where to listen?

Podcasts in the app Replaio Radio Coming soon

Podcasts are coming to the app soon. Install now and be the first to see a whole new take on podcasts

Get it on Google Play Install for free Android 10M+ downloads · 4.7+ rating iOS soon

Episodes

Fast Adaptation of Behavioral Foundation Models 14.04.2025

This paper from the University of Texas at Austin, FAIR at Meta, and UMass Amherst introduces methods for rapidly improving the performance of pre-trained reinforcement learning agents, known as Behavioral Foundation Models (BFMs), on new tasks. While BFMs can initially solve diverse tasks without further learning, their zero-shot performance is often suboptimal. The authors propose two fast adapt...

Proprietary Reward Models: Sustaining Advantage in Agentic AI 13.04.2025

We posit that as foundational AI technologies and tool access become increasingly democratized,  proprietary reward models  will become a key source of  sustainable competitive advantage . These models, representing codified organizational knowledge and strategic principles for guiding AI agents, are argued to be  difficult for competitors to replicate  due to their reliance on unique data, tacit...

Why Multi-Agent LLM Systems Fail: A Comprehensive Study 12.04.2025

This paper,  "Why Do Multi-Agent LLM Systems Fail?" , presents a comprehensive study into the shortcomings of systems where multiple large language model agents collaborate. Through extensive analysis of several popular multi-agent frameworks across numerous tasks, the authors  identify and categorize 14 distinct failure modes  into three main areas: specification/design flaws, inter-age...

Play2Prompt: Zero-Shot Tool Instruction Optimization via Tool Play 12.04.2025

This paper  introduces  Play2Prompt , a new method for enhancing how large language models utilize external tools in zero-shot settings. This framework  automatically refines tool documentation and generates usage examples  by having the LLM "play" with the tools in a trial-and-error manner. Through this  iterative process of interaction and self-reflection , Play2Prompt improves the LLM...

Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems 12.04.2025

This extensive survey explores the burgeoning field of  intelligent agents powered by large language models , examining their design through a  brain-inspired modular architecture . The authors systematically investigate  core agent components ,  mechanisms for self-enhancement and adaptation , and the dynamics of  collaborative multi-agent systems . A significant portion of the work addresses the...

API and GUI Agents: Divergence, Convergence, and Hybrid Approaches 12.04.2025

This research paper compares and contrasts two types of software agents powered by large language models (LLMs): API-based agents and GUI-based agents .  API agents interact with software through programmatic interfaces , offering efficiency and reliability, while  GUI agents mimic human interaction by operating through graphical user interfaces , providing flexibility and broader applicability. T...

AI, Chess, and Competitive Advantage: Substitution and Complementation 12.04.2025

This academic article from the Strategic Management Journal investigates  how artificial intelligence (AI) alters the foundations of competitive advantage  by examining chess tournaments involving human players, AI engines, and human-AI teams. The authors apply a  resource-based view  to analyze how AI adoption leads to both the  substitution of traditional human cognitive skills  and the  emergen...

Knowledge of the Firm and Replication of Technology 12.04.2025

Kogut and Zander (1992)  argue that a firm's existence is better understood through its ability to create, share, and transfer knowledge, both explicit and tacit, rather than solely as a mechanism to reduce transaction costs. They emphasize that this organizational knowledge, embedded in cooperative principles, drives firm capabilities and influences strategic decisions like make-or-buy. The autho...

Firm Resources and Sustained Competitive Advantage 12.04.2025

This academic paper introduces the resource-based view of sustained competitive advantage.  It argues that  differences in firms' resources and capabilities are key drivers of their success over time.  The author  defines critical concepts like firm resources, competitive advantage, and sustained competitive advantage.  The paper  explores conditions under which firm resources can lead to last...

Evaluating Pharmaceutical Marketing to Physicians with Panel Data 12.04.2025

This paper by Mizik and Pavlov explores the application of  panel data methods  in marketing research, emphasizing their advantages over cross-sectional and time-series data by addressing  individual heterogeneity  and  dynamic processes . The authors discuss various  static and dynamic panel data models , including random effects and fixed effects, and highlight potential  estimation issues and b...

Theory of the firm in the era of Agents 12.04.2025

We discuss the economic theory of the firm in the era of agents.

Large Language Models: An Applied Econometric Framework 12.04.2025

This working paper from the National Bureau of Economic Research introduces an  applied econometric framework for understanding and utilizing large language models (LLMs) in economic research . The authors address two primary empirical applications:  prediction and estimation . For prediction tasks, they highlight the critical issue of  training leakage , where LLMs may have been trained on the ve...

Evaluating the World Model Implicit in a Generative Model 12.04.2025

This paper ( [2406.03689] Evaluating the World Model Implicit in a Generative Model ) investigates how to evaluate if generative models, particularly large language models, truly learn underlying "world models" of the data they are trained on, which are formalized here as deterministic finite automata. The authors introduce new metrics inspired by the Myhill-Nerode theorem to assess whet...

Machine Learning for Hypothesis Generation in Social Science 11.04.2025

Researchers explored a novel method for generating scientific hypotheses using machine learning algorithms applied to extensive human behavior data.  This approach moves beyond relying solely on individual researchers' insights.  Their framework demonstrates the ability of machine learning to uncover correlations that human analysis might miss, especially in complex datasets.  To illustrate th...

Active Learning for Moral Preference Elicitation: Challenges and Nuances 11.04.2025

We explore the efficacy of  active learning  for understanding  moral preferences , which are people's views on right actions when harm is involved. While active learning efficiently learns preferences in some areas, the authors argue it relies on assumptions like  stable preferences, accurate models, and limited response noise , which may not hold for moral judgments. Through  simulations  te...

Gradient-Based Surveys for Nonparametric Discrete Choice Experiments 11.04.2025

This paper  introduces Gradient-based Survey (GBS), a novel method for designing products based on consumer preferences.  Unlike traditional approaches, GBS adaptively generates paired comparison questions for consumers using gradient-based machine learning, eliminating the need for a predefined utility model.  This allows GBS to effectively handle products with numerous attributes and to personal...

Explainable Data-driven Share-of-choice Product Line Design Optimization 11.04.2025

This research introduces a new methodology for product line design that directly incorporates customer survey data, specifically from conjoint analysis, into the optimization process. This contrasts with traditional methods that first estimate customer preferences and then use these estimations for design. The authors propose a robust model that maximizes the share-of-choice by considering the wor...

The More You Ask, the Less You Get: When Additional Questions Hurt External Validity 11.04.2025

This research paper explores how the act of answering multiple, similar preference elicitation questions can ironically diminish the accuracy of predicting real-world behavior. The authors argue that as respondents answer more questions, they adapt and employ task-specific decision-making processes that may not align with how they make choices in different contexts. Using methods like mouse tracki...

Conjoint topics from Handbook of Marketing Analytics: Methods and Applications 11.04.2025

We discuss conjoint-related chapters from Handbook of Marketing Analytics.  It features contributions from leading scholars and industry experts, covering topics from  experimental design and conjoint analysis to time-series modeling and machine learning.  The text examines these methodologies in various contexts, including  public policy, litigation support, and understanding consumer behavior.  ...

Choice-Based Conjoint Analysis: Methods and Applications 11.04.2025

This handbook entry comprehensively explains  Choice-Based Conjoint Analysis (CBC) , a popular market research technique for understanding consumer preferences. It details the  theoretical underpinnings , including utility and choice models, and outlines the  practical steps  involved in conducting CBC experiments, from attribute selection to questionnaire implementation. The text further explores...

Beyond Conjoint Analysis: The Future of Preference Measurement 11.04.2025

The survey "Beyond Conjoint Analysis: Advances in Preference Measurement"  reviews the evolution of preference measurement beyond traditional conjoint analysis. The authors propose a framework centered on the problem, task design, and model specification, highlighting recent research and future directions for each component. The paper discusses the expanding applications of preference me...

An Optimization Framework for Adaptive Questionnaire Design 11.04.2025

This paper by J. Abernethy et al. (2004) introduces a novel optimization framework for adaptive questionnaire design, specifically for conjoint analysis, where questions are tailored to individual respondents based on their previous answers. This approach iteratively refines the questionnaire using principles from statistical learning theory, aiming to efficiently and accurately capture individual...

Adaptive Self-Explication of Multiattribute Preferences 11.04.2025

This 2011 paper by Oded Netzer  and  V. Srinivasan introduces  Adaptive Self-Explication (ASE) , a new web-based method for measuring consumer preferences across many product attributes.  ASE improves upon traditional self-explicated methods  by having users rank attributes and then complete a sequence of adaptively chosen constant-sum paired comparisons.  Two studies, on digital cameras and lapto...

Conjoint Analysis: Methods, Applications, and Recent Developments 11.04.2025

Conjoint analysis , a significant marketing research technique, helps understand how customers make choices by evaluating trade-offs between product or service attributes like features and price. This method, widely used since 1971, aids in decisions such as  product design, pricing, and market segmentation  by quantifying the value consumers place on different attribute levels. Various types of c...

Current Issues and a “Wish List” for Conjoint Analysis 11.04.2025

This paper, by Professor Bradlow, presents a "wish list" of unresolved issues and potential future research directions for conjoint analysis, a widely used marketing tool. This prompts commentary from several experts (Magidson, Vermunt, Louviere, Orme, and Swait), who offer their perspectives on Bradlow's points, sometimes agreeing, sometimes disagreeing, and highlighting existing re...

Listen to the Best AI papers explained podcast in Replaio

Radio and podcasts in one app - free, with no sign-up. Install today and do not miss the launch

Get it on Google Play

Replaio is not a podcast publisher; show names, artwork and audio belong to their authors and are distributed through public RSS feeds.