Best AI papers explained

This paper investigates the limitations of large language models (LLMs) as evaluators when directly scoring natural language generation quality, finding that existing calibration methods are insufficient to align their judgments with humans. Inspired by preference-based training in RLHF, the authors propose Pairwise-preference Search (PAIRS) , an efficient, scalable method that reframes evaluation...

This paper exemines the performance of Large Language Models (LLMs) in multi-turn conversations compared to single-turn interactions. The authors developed a method to create "sharded" instructions from fully-specified tasks, allowing for controlled simulation of underspecified, multi-turn exchanges. They discovered that LLMs exhibit significantly lower performance and drastically increa...

This academic paper, arXiv:2503.05070 , introduces PromptPex , a tool designed to automatically generate and evaluate unit tests for language model prompts . The authors highlight that prompts function similarly to traditional software but require new testing methods due to their dependency on the specific AI model interpreting them. PromptPex extracts specifications from a prompt to create varied...

Jonathan Richens, David Abel, Alexis Bellot and Tom Everitt This paper focuses on the necessity of world models for creating general and capable AI agents , specifically those that can generalize to multi-step goal-directed tasks. The authors formally demonstrate that any agent capable of this type of generalization must have learned a predictive model of its environment , and that the accuracy of...

This paper examines the reasoning capabilities of Large Reasoning Models (LRMs) compared to standard Large Language Models (LLMs) by testing them on controlled puzzle environments . The researchers found that LRM performance collapses entirely beyond a certain complexity, and surprisingly, their reasoning effort decreases as problems become too difficult. The study reveals three complexity regimes...

This excerpt from a handbook chapter explores the evolving landscape of decision-making in the information age, highlighting the increasing collaboration between humans and algorithms . It outlines a three-stage model of human decision processes when unaided and discusses how bounded rationality leads to the use of heuristics and intuitive judgments when resources are limited. The text further cat...

This paper presents a causal framework for supervised domain adaptation , addressing how models can effectively generalize from source domains with abundant data to a target domain with limited examples. The authors propose structure-informed procedures that utilize knowledge of the underlying causal structure and domain discrepancies to transport inferences , achieving faster adaptation rates tha...

This academic paper proposes **Conformal Arbitrage (CA)**, a post-deployment framework for **balancing competing objectives** in language models, such as helpfulness versus harmlessness or cost versus accuracy. CA uses a **data-driven threshold** calibrated with conformal risk control to decide when to use a potentially faster or cheaper "Primary" model optimized for a primary goal and w...

This paper introduces a simulation-based method for statistical inference in adaptive experiments , specifically addressing challenges that arise when analyzing data from multi-arm bandit designs. Unlike traditional randomized trials, adaptive designs modify treatment assignments during the experiment, which can complicate standard inference techniques. The proposed approach, called simulation wit...

This position paper explores the evolution of Large Language Models into autonomous agents, proposing a unified theory that views both internal reasoning and external actions as equivalent tools for acquiring knowledge. The authors argue that for optimal behavior, an agent's decision boundary for using tools should align with its knowledge boundary , only resorting to external tools when inter...

This paper introduces quantitative LLM judges , a new approach for evaluating the output of large language models (LLMs) that aims to improve upon the "LLM-as-a-judge" framework. The core idea is to decouple the qualitative reasoning provided by an LLM judge (its textual evaluation) from the quantitative scoring . The framework utilizes a two-stage process where a frozen LLM provides a t...

This paper describes the Self-Challenging framework , a method for training large language model (LLM) agents to use tools by generating their own training tasks. The framework involves the agent acting as a "challenger" to create tasks and then as an "executor" to solve them using reinforcement learning. To ensure task quality, the paper introduces the "Code-as-Task"...

This paper introduces In-Context Pure Exploration (ICPE) , a novel deep learning framework designed to learn exploration strategies for active sequential hypothesis testing . Unlike traditional methods that rely on explicit problem-specific algorithms, ICPE uses a Transformer architecture to infer the underlying problem structure directly from experience. The framework combines supervised and rein...

This document investigates why bidirectional language models perform better than unidirectional models on natural language understanding tasks. The authors propose a new framework called Flow Neural Information Bottleneck (FlowNIB) , which uses the Information Bottleneck principle to analyze the flow of information during training. FlowNIB dynamically balances maximizing information about the inpu...

This academic paper examines the faithfulness of chain-of-thought (CoT) reasoning in large language and vision-language models, specifically looking at how different types of biases affect model behavior and whether these biases are reflected in the models' CoTs. The research introduces a novel evaluation framework to analyze bias articulation and identifies a phenomenon of "inconsistent...

This academic paper introduces FIBO , a novel approach to Bayesian optimization (BO) that significantly streamlines the process . Traditional BO relies on sequentially building surrogate models and optimizing acquisition functions, which can be computationally expensive and time-consuming . FIBO bypasses these steps by employing a pretrained deep generative model that directly samples from the pos...

This paper from Google Research investigates the ability of large language models (LLMs) to perform probabilistic reasoning in interactive settings, specifically focusing on their capacity to infer user preferences over multiple interactions. The research finds that off-the-shelf LLMs struggle with this task compared to an optimal Bayesian model , demonstrating limited improvement as more informat...

This paper details an innovative method for improving vision-language models (VLMs) by leveraging large language models (LLMs) to optimize the text prompts used in tasks like image classification. Current methods for prompt learning in VLMs can suffer from issues like lack of interpretability and overfitting. The proposed approach, termed Interpretable Prompt Optimization (IPO) , uses an LLM as a...

This paper introduces an innovative framework using an evolutionary algorithm to optimize prompts for vision-language models without requiring additional training. The method evolves prompts through iteration and selection to elicit complex multimodal reasoning abilities , such as breaking down tasks and employing external tools like Python interpreters for image manipulation. Experimental results...

This paper examines a fundamental limitation in evaluating large language models (LLMs): current methods primarily assess only their observable outputs, neglecting a potentially vast amount of unseen knowledge embedded within them. To address this, a research paper introduces KnowSum , a statistical framework that estimates this hidden knowledge by extrapolating from the frequency of observed outp...

This document introduces  CFGRL , a novel framework that bridges generative modeling, specifically diffusion guidance, and reinforcement learning. The core idea is to treat policy improvement as guiding a diffusion model, allowing for  simple training  akin to supervised learning while still enabling  performance beyond the initial dataset . CFGRL can improve policies by combining a reference poli...

This academic paper presents Alita , a novel generalist agent designed to enhance scalable agentic reasoning with a focus on minimal predefinition and maximal self-evolution . Unlike conventional agents that rely heavily on pre-designed tools and workflows, Alita utilizes a radically simple design with a core web agent and the ability to autonomously generate, refine, and reuse capabilities via Mo...

This academic paper proposes a local data attribution framework for online reinforcement learning (RL) . The framework uses influence functions to identify which training data records negatively impact the RL agent's learning within each training round. By filtering out these harmful records , the proposed method, called Influence-guided Intervention and Filtering (IIF) , demonstrates improved...

This paper presents a theoretical analysis of how transformers can learn k-fold composition tasks , which involve combining multiple permutations. It proposes that transformers can achieve this through a hierarchical process , where each layer learns progressively more complex compositions, referred to as " hops ." The document details a curriculum learning strategy (Algorithm 1) and a m...

This academic paper introduces a new approach to preference learning by  incorporating response time data  alongside traditional binary choices. The authors highlight that while standard preference learning relies solely on which option a user prefers, the  speed of the decision can provide valuable information  about the strength of that preference. They propose novel methodologies, including a ...