All notes, newest first
2,343 notes. Notes 851 to 900, page 18 of 47.
From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search
Researchers have proposed a new method called Multi-Agent Protocol Distillation (MAPD) to improve the performance of large language models in solving knowledge-intensive tasks. This method addresses the challenge of…
From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search
Researchers propose Multi-Agent Protocol Distillation (MAPD), a method to bridge the gap between open-source and proprietary language models in solving knowledge-intensive tasks. MAPD uses a structured protocol as an…
Gubernaut: A Deterministic Homeostatic Controller for Affect-Regulated LLM Agents, Validated Across Independent Model Families
The research presents a new model-agnostic controller, Gubernaut Cognitive Controller (GCC), designed to control the behavior of Large Language Model (LLM) agents. The GCC aims to mitigate reactive failure modes in…
Gubernaut: A Deterministic Homeostatic Controller for Affect-Regulated LLM Agents, Validated Across Independent Model Families
The research introduces Gubernaut Cognitive Controller (GCC), a model-agnostic runtime control layer designed to regulate the behavior of large language models (LLMs) that can exhibit reactive failure modes such as…
KANEx: Translating Kolmogorov-Arnold Networks' Interpretability to Medical Explainability
A new framework, KANEx, is introduced to leverage the inherently interpretable components of Kolmogorov-Arnold Networks (KANs) for generating more reliable textual explanations in chest X-ray classifiers. The approach…
LEX-EC: A Lexical Evidence-Channel Audit Framework for Zero-Shot LLM Personality Classification in Black-Box Settings
Researchers introduce LEX-EC, a framework for analyzing the interpretability of large language models in assigning personality labels from text. The framework identifies and separates marginal distribution effects from…
LLM-Assisted Ontology Engineering and Construction of a French Legal Knowledge Graph
The paper describes a two-stage workflow for creating a French legal knowledge graph, specifically for maintenance regulations. The first stage involves open extraction of entities and triples from a corpus using LLM…
LLM-SoccerArena: Benchmarking LLMs on Real-World Predictions in Sports
LLM-SoccerArena is a new platform that allows for the prospective evaluation of large language models' abilities to forecast real-world sports events before their outcomes are known. The platform provides a live…
Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic Code Repair
The paper discusses the unreliability of looping in coding agents and the challenge of ensuring that correct patches are retained, verified, and submitted. The authors conducted several studies to understand this gap…
Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic Code Repair
The paper explores the lack of reliability guarantees in coding agents that use generate-test-revise loops. The authors conduct studies to understand the gap between finding a correct patch and retaining, verifying…
Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic Code Repair
The paper discusses the unreliability of generating-test-revise loops in coding agents, focusing on the gap between finding a correct patch and actually implementing it. The study reveals that using stale traces can…
Making Mathematical Knowledge Explainable, Accessible and Interoperable Through Large Language Model Integration
The authors propose integrating Large Language Models (LLMs) with a mathematical knowledge base called MathModDB to improve its accessibility, explainability, and interoperability. The integration is achieved through a…
Myopia Prevention and Control 3.0: Artificial Intelligence--Driven Risk Stratification, Proactive Monitoring, and Personalized Intervention
The authors discuss Myopia Prevention and Control 3.0, a new approach that leverages artificial intelligence (AI), digital sensing, and ubiquitous computing to transform the way myopia is managed. This approach aims to…
Physics-Guided Generative AI for Property-Targeted 3D Porous Media Design
The paper proposes a new framework using physics-guided generative AI to design three-dimensional porous media. The goal is to improve applications in various fields such as filtration, energy storage, and biomedical…
Reason-Mediated Behavioral Models for Auditing LLM Social Simulators
Researchers propose a new method to evaluate large language models used as social simulators, including synthetic survey respondents. They argue that existing evaluation methods are insufficient because these models…
Reason-Mediated Behavioral Models for Auditing LLM Social Simulators
Researchers propose a method to evaluate large language models used as social simulators, such as synthetic survey respondents. They argue that simply checking if the simulated outcomes match human outcomes is not…
Regulating for AI Legitimacy
The article discusses the issue of AI governance, specifically focusing on the question of legitimacy rather than just alignment. The author argues that AI systems already have significant influence in areas like…
Simulating Tenant Responses to Energy Policy Interventions with Transaction-Cost-Aware LLM Age
Researchers developed a method to simulate how tenants respond to energy-efficient renovation policies using large language models (LLMs). They introduce a friction-aware persona modeling approach that takes into…
SIREN: Towards End-to-End Extreme-Weather Early Warning with Experience-Grounded LLM Agents
The study presents SIREN, a framework for automating end-to-end extreme-weather early warning using Large Language Model (LLM) agents. The researchers developed SIREN-Bench, a comprehensive benchmark, and found…
SIREN: Towards End-to-End Extreme-Weather Early Warning with Experience-Grounded LLM Agents
Researchers are working on an automated system called SIREN to improve extreme weather early warning systems using Large Language Model (LLM) agents. The system is designed to bridge the gap between isolated scientific…
Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects
A study explores the inconsistencies in linking sparse autoencoders (SAEs) with model behavior, focusing on the geometry of changes in model logits caused by feature interventions. The authors propose an unsupervised…
Task-Conditional Faithfulness Auditing of Multimodal LLMs for Grid Diagnosis
The paper proposes a framework for auditing multimodal large language models used in grid diagnosis tasks to ensure they are using task-appropriate evidence. The framework compares self-reported reliance, behavior…
Teacher Knows It Best: Spontaneous Symmetry Breaking and Tipping Points in Networked Langevin Dynamics AI Sycophancy
Researchers have developed a statistical physics framework to study a networked stochastic system exhibiting bistability, which can be used to understand and address AI-induced delusional spiraling, a phenomenon where…
Teacher Knows It Best: Spontaneous Symmetry Breaking and Tipping Points in Networked Langevin Dynamics AI Sycophancy
Researchers present a statistical physics model for a networked stochastic system with bistability, applied to address AI-induced delusional spiraling. The model partitions the network into regular agents and 'aware'…
The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation
The paper focuses on improving the multi-turn long-horizon planning for foundation model agents. The authors introduce a controlled environment to study the acquisition, shaping, and integration of planning abilities…
The Tokenizer Tax: Quantifying and Explaining the Cross-Lingual Cost of Subword Tokenization for Indian Languages
The research quantifies the disadvantage faced by many non-English languages in large language models (LLMs) due to subword tokenizers that are primarily trained on English corpora. The study focuses on Indian…
AITE Overview
NIST's AITE program provides a sequestered environment for evaluating AI models on blind data and common tasks, with the goal of reducing train/test contamination and improving comparability.
Agent-Guided Relational Concept Discovery: Toward Interpretable Surgical Margin Assessment
Researchers propose a new framework called Agent-Guided Concept Discovery to improve the clinical adoption of deep learning models for surgical margin assessment using Rapid Evaporative Ionization Mass Spectrometry…
Agent-Guided Relational Concept Discovery: Toward Interpretable Surgical Margin Assessment
Researchers propose a new method called Agent-Guided Concept Discovery to help deep learning models assess surgical margins more effectively, particularly in noisy and unlabeled data acquired during surgery. The…
Agent-Guided Relational Concept Discovery: Toward Interpretable Surgical Margin Assessment
Researchers propose Agent-Guided Concept Discovery, a framework that helps deep learning models interpret REIMS data for surgical margin assessment by learning meaningful concepts directly from data without predefined…
Agent-Guided Relational Concept Discovery: Toward Interpretable Surgical Margin Assessment
Researchers propose a new framework called Agent-Guided Concept Discovery for improving deep learning models used in surgical margin assessment. The model learns meaningful concepts directly from data without requiring…
Agentic coding without the cloud: evaluating open-weight large language models on longitudinal data preparation tasks
Researchers have developed an open-source framework to evaluate the effectiveness of AI agents powered by open-weight large language models (LLMs) in data preparation tasks for longitudinal population studies. The…
Agentic coding without the cloud: evaluating open-weight large language models on longitudinal data preparation tasks
Researchers introduced an open-source framework to evaluate the effectiveness of AI agents powered by open-weight large language models (LLMs) in data preparation tasks for longitudinal population studies. The study…
Agentic coding without the cloud: evaluating open-weight large language models on longitudinal data preparation tasks
Researchers have developed an open-source framework for evaluating the effectiveness of AI agents powered by open-weight large language models in data preparation tasks, specifically focusing on longitudinal population…
Agentic coding without the cloud: evaluating open-weight large language models on longitudinal data preparation tasks
Researchers introduce an open-source framework for evaluating the effectiveness of AI agents powered by open-weight large language models (LLMs) in data preparation tasks, specifically for longitudinal population…
Agentic coding without the cloud: evaluating open-weight large language models on longitudinal data preparation tasks
Researchers have developed an open-source framework for evaluating the effectiveness of AI agents powered by large, locally deployable language models (LLMs) in data preparation tasks, specifically focused on…
Agentic coding without the cloud: evaluating open-weight large language models on longitudinal data preparation tasks
The study introduces an open-source framework for evaluating the effectiveness of AI agents powered by open-weight large language models (LLMs) in data preparation tasks, particularly for longitudinal population…
Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems
A research paper suggests a new approach to managing AI agents' reasoning context, which includes conversation histories, large prompts, and tool definitions. The authors argue that this should be treated as a…
Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems
The paper proposes a new approach for managing AI agent context, arguing that it's not just a storage-and-retrieval problem but a lifecycle issue involving deciding what to remember, structuring it, choosing the right…
Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems
The article proposes a new discipline called Agentic Context Management (ACM) to address issues faced by AI agents in managing their reasoning context, such as conversation histories and large prompts. The authors…
Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems
The paper discusses Agentic Context Management (ACM), a new approach to managing the context in which AI agents operate. It argues that current methods for managing an agent's context, such as storing and retrieving…
Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems
The paper presents Agentic Context Management (ACM), a solution to the issue of AI agents being overwhelmed by their own accumulating history and growing token cost in production settings. The authors argue that…
AI Assistants Overassist
Researchers introduce Int-Bench, a benchmark to evaluate AI language models (LLMs) as tutors or thought partners during problem-solving. The study reveals that LLMs intervene more frequently and earlier than humans…
AI Assistants Overassist
The study introduces Int-Bench, a benchmark for evaluating AI systems as tutors and thought partners. The researchers compare large language models (LLMs) to humans in terms of intervention frequency, timing, and…
AI Assistants Overassist
Researchers introduce Int-Bench, a tool to evaluate how AI language models intervene during problem-solving tasks across code debugging, mathematics, and brain teasers. The study finds that AI models provide more…
AI Assistants Overassist
The text discusses a study evaluating how AI language models, used as tutors or thought partners, intervene during problem-solving. The study introduces Int-Bench, a simulation-based benchmark for assessing these…
AREX: Towards a Recursively Self-Improving Agent for Deep Research
The paper introduces a new type of research agent called AREX, which can recursively improve its answers by verifying intermediate results and using the partially verified state to guide subsequent refinement. The…
AREX: Towards a Recursively Self-Improving Agent for Deep Research
The paper introduces a new family of agents called AREX for deep research. These agents are designed to recursively improve their answers by verifying intermediate results, guiding subsequent refinement, and learning…
AREX: Towards a Recursively Self-Improving Agent for Deep Research
The paper introduces a new type of deep research agent called AREX. These agents are designed to recursively improve their answers by verifying intermediate results, using the partially verified state to guide…
Beyond Sycophancy: Structured Resistance and Compliance in LLM Moral Reasoning
The authors investigate how large language models can learn from others without merely conforming to them, focusing on the distinction between incorporating others' perspectives and maintaining a well-grounded moral…
Page 18 of 47
