All notes, newest first
2,343 notes. Notes 601 to 650, page 13 of 47.
Reducing belief in conspiracy theories as they unfold using large language models
Researchers tested if conversations with a large language model (LLM) can reduce belief in emerging conspiracy theories. They conducted experiments in the days following two significant events, and found that…
Reducing belief in conspiracy theories as they unfold using large language models
A study conducted by Costello et al. explores the use of large language models (LLMs) in reducing belief in conspiracy theories that emerge following major events, such as the assassination attempts on Donald Trump and…
Resourced Authority A Mechanism-Design Model for Participatory Governance of Deployed AI Agents
The authors propose a formal model for continuous participatory governance of AI agents, focusing on resource allocation as a means to enforce authorization through compute budgets. The aim is to establish a 'Safe AI'…
Resourced Authority A Mechanism-Design Model for Participatory Governance of Deployed AI Agents
The authors propose a model for continuous participatory governance of AI agents, focusing on controlling them through resource allocation to make authorization self-enforcing via compute budgets. The model consists of…
Resourced Authority A Mechanism-Design Model for Participatory Governance of Deployed AI Agents
The authors propose a model for continuous participatory governance of AI agents through resource allocation, specifically compute budgets, to make authorization self-enforcing. The model is designed as a compliance…
Resourced Authority A Mechanism-Design Model for Participatory Governance of Deployed AI Agents
The paper presents a model for continuous participatory governance of deployed AI agents, focusing on resource allocation (compute budgets) as a means to enforce authorization and ensure safe AI. The mechanism involves…
Schema-Guided Hierarchical Information Extraction and Semantic Evaluation Using Generative AI
Researchers have developed a new method for extracting complex, structured information from unstructured text documents using generative AI. The method involves creating a schema that serves as an information model…
Schema-Guided Hierarchical Information Extraction and Semantic Evaluation Using Generative AI
Researchers have developed a framework using generative AI to extract complex, structured information from unstructured text documents. This framework also includes an automated semantic evaluation step to compare the…
The Illusion of Visual Tool-Use: A Causal Audit of Thinking with Images
Researchers audit the effectiveness of using visual tools like crop-and-zoom in multimodal language models by creating a causal graph to separate observation-mediated paths from action-induced shortcuts. They find that…
The Illusion of Visual Tool-Use: A Causal Audit of Thinking with Images
The study examines the 'thinking-with-images' paradigm used in multimodal Language Models (LLMs), which includes visual operations like crop-and-zoom. The research finds that these operations often result in minimal or…
Tracing the Heart: An Evidence-Linked Pipeline for Heart-Failure Feature Engineering
Researchers developed an automated system called nMAS for heart-failure feature engineering in electronic health records (EHR). The system generates structured and aggregated features that were verified and audited…
Tracing the Heart: An Evidence-Linked Pipeline for Heart-Failure Feature Engineering
Researchers developed an AI system called nMAS to automate the process of extracting structured and aggregated features from Electronic Health Records (EHR) for heart failure research. The system generates these…
Tracing the Heart: An Evidence-Linked Pipeline for Heart-Failure Feature Engineering
Researchers have developed an evidence-linked pipeline called Nimblemind Multi-Agent System (nMAS) to automate heart-failure feature engineering for electronic health record data. The system generates structured and…
Tracing the Heart: An Evidence-Linked Pipeline for Heart-Failure Feature Engineering
Researchers have developed a system called nMAS for automating heart-failure feature engineering in electronic health records (EHRs). The system generates structured and aggregated features that improve the accuracy of…
TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories
The paper proposes a framework called TrajDebug to improve error detection in long-term AI agent trajectories. It addresses the challenges of identifying errors in lengthy trajectories and multiple local errors with…
TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories
In this study, the authors propose a framework named TrajDebug to identify critical errors in long-horizon agent trajectories, which are complex systems that can perform tasks but often suffer from cascading errors…
TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories
The paper presents TrajDebug, a framework designed to trace error lifecycles in long-horizon AI agents. The goal is to identify critical failures by compressing history and using evidence-based error identification…
TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories
The paper proposes TrajDebug, a framework for error-lifecycle tracing in long-trajectory agentic systems. The goal is to identify critical errors responsible for final failures, especially in complex domains where…
TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories
In this study, researchers present TrajDebug, a framework designed to identify critical errors in long trajectories of large language models (LLM) used in complex domains. The framework addresses two challenges: first…
TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories
The paper proposes TrajDebug, a framework designed to trace errors in long-term AI agent trajectories. The framework addresses challenges in identifying individual errors in long trajectories and distinguishing…
Tytan: Interactive Neurosymbolic Construction of Analytic Semantic Schemas from Relational Data
The paper presents Tytan, a system that automatically constructs an analytic semantic schema from relational databases to improve data analysis tools. The system combines symbolic analysis and LLM-based semantic…
Tytan: Interactive Neurosymbolic Construction of Analytic Semantic Schemas from Relational Data
Researchers have developed a system called TYTAN that can automatically construct an analytic semantic schema from a relational database, helping to reduce the need for manual knowledge acquisition and potentially…
Tytan: Interactive Neurosymbolic Construction of Analytic Semantic Schemas from Relational Data
The paper presents TYTAN, a system that automatically generates an analytic semantic schema from a relational database and user-provided descriptions. It combines symbolic analysis with LLM-based semantic inference for…
Tytan: Interactive Neurosymbolic Construction of Analytic Semantic Schemas from Relational Data
TYTAN is a system that automatically constructs an analytic semantic schema from a relational database, with user-provided descriptions when available. It uses symbolic analysis and LLM-based semantic inference for…
What Current AI Benchmarks Leave Unmeasured: Modality, Search, Citations, and Implications (for Safety Evaluations)
The study audits the assumptions made in large language model (LLM) benchmark evaluations, focusing on one popular LLM - ChatGPT. The research compares two access modalities (chat UI and API), with and without web…
What Current AI Benchmarks Leave Unmeasured: Modality, Search, Citations, and Implications (for Safety Evaluations)
The research examines the limitations of current benchmarks used to evaluate large language models (LLMs) for safety, reliability, and deployment readiness. The study focuses on a popular LLM, ChatGPT, comparing its…
What Current AI Benchmarks Leave Unmeasured: Modality, Search, Citations, and Implications (for Safety Evaluations)
The study compares two access modalities of a large language model (LLM), ChatGPT's chat UI and OpenAI's API, with and without web search enabled. The research shows that the accuracy of responses varies between the…
What Current AI Benchmarks Leave Unmeasured: Modality, Search, Citations, and Implications (for Safety Evaluations)
The study examines the limitations of current AI benchmarks by focusing on factors such as modality (chat UI vs API), search capabilities, consistency of responses, citation grounding, and abstention behavior using…
A Chain Is Only as Strong as Its Weakest Link: A Scoping Review of System Integration Audits in AI
A study reviews 58 AI audits that focus on system integration, finding that while few measures address integration-specific risks and significant gaps remain in traditional audit expectations, integration can be…
A-SR: Self-Evolving Agentic LLMs for Symbolic Regression via Hierarchical Coordination
Researchers have developed a new framework called A-SR for symbolic regression. This framework uses a self-evolving agentic system that shifts control from expression edits to role-conditioned evidence views. It…
A-SR: Self-Evolving Agentic LLMs for Symbolic Regression via Hierarchical Coordination
A research paper introduces a new framework called A-SR for symbolic regression. A-SR is designed to discover closed-form equations from data and uses a self-evolving agentic system that coordinates formula discovery…
ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment
The paper proposes a new method called Answer-Backtracked Credit Assignment (ABC) for training long-horizon search agents that make multiple sequential actions to reach an answer. ABC focuses on rewarding useful…
ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment
Researchers have proposed a new method called Answer-Backtracked Credit Assignment (ABC) to train long-horizon search agents more effectively. This method converts sparse trajectory-level outcomes into dense step-level…
ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment
Researchers propose a method called Answer-Backtracked Credit Assignment (ABC) to train long-horizon search agents more effectively. This method converts sparse trajectory-level outcomes into dense step-level…
Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation
Researchers propose Observation-Calibrated Self-Distillation (OCSD) to address a confounding issue in On-Policy Self-Distillation (OPSD), a method used to train large language model agents. OCSD aims to attribute…
Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation
Researchers propose a new method called Observation-Calibrated Self-Distillation (OCSD) to train large language models in reinforcement learning. OCSD addresses a confounding issue in previous methods by comparing two…
Argus: A General-Purpose Agentic Runtime for Long-Horizon Reasoning
The paper introduces Argus, a persistent and self-evolving runtime system designed for long-term reasoning. This system separates stable user intent from operational objectives and allows for the addition of various…
Argus: A General-Purpose Agentic Runtime for Long-Horizon Reasoning
The paper presents Argus, a runtime system designed for long-term reasoning by an agent. It allows the system to maintain its approach when evidence supports it and change direction based on measurements that indicate…
Argus: A General-Purpose Agentic Runtime for Long-Horizon Reasoning
The paper introduces Argus, a persistent, self-evolving runtime system designed for long-horizon reasoning. Argus consists of Manager, Planner, Engineer, and Reviewer that execute bounded missions over durable project…
ArtAnno: Annotating Implicit Semantics in Artworks through LLM Agent-Driven Bidirectional Human-AI Augmentation
Researchers have developed a new system called ArtAnno to help with annotating artworks more efficiently. The system uses a bidirectional Human-AI Augmentation (BiHAA) framework, which allows both the AI and human…
ArtAnno: Annotating Implicit Semantics in Artworks through LLM Agent-Driven Bidirectional Human-AI Augmentation
The paper presents ArtAnno, a system that uses a bidirectional human-AI augmentation (BiHAA) framework to improve the efficiency of artwork annotation. This system helps experts by suggesting semantic labels and learns…
Chained Recursive Language Models for Multi-Iteration Reasoning
The paper proposes a new architecture for large language models called Chained Recursive Language Models (Chained RLM). This architecture is designed to handle long context reasoning tasks that require extraction…
Chained Recursive Language Models for Multi-Iteration Reasoning
The paper proposes Chained Recursive Language Models (Chained RLM), an architecture for multi-iteration reasoning in large language models (LLMs). It addresses the difficulty in tasks requiring extraction, counting…
CheMLFlow: An Open-Source Platform for Cheminformatics and Materials Informatics Applications
CheMLFlow is an open-source platform designed to facilitate the creation and execution of end-to-end, high-throughput workflows for scientific and technological applications. It aims to streamline the process of…
CheMLFlow: An Open-Source Platform for Cheminformatics and Materials Informatics Applications
CheMLFlow is an open-source platform designed to help researchers build end-to-end, high-throughput, and agentic workflows for various scientific and technological applications. It aims to address the common challenge…
Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning
The paper introduces CoCoEvolve, a method aimed at improving the consistency between chart, table, and code representations in AI systems. The method optimizes models based on agreement between different…
ContextWeave: A Real-World Workflow Benchmark
Researchers introduce ContextWeave, a new benchmark for evaluating the performance of language agents in long-horizon, stateful workflows. The benchmark measures how well an agent can recall and apply past experiences…
ContextWeave: A Real-World Workflow Benchmark
The paper introduces ContextWeave, a new benchmark for evaluating the performance of language agents in long-horizon, stateful workflows. The benchmark focuses on memory as an essential component and measures workspace…
CoPlan: A Trustworthy Co-Intelligence Interface for Care Planning through Role-Based Contestable Argument Graphs
CoPlan is a new AI system designed to help with care planning for clinicians, patients, caregivers, and care teams. It allows stakeholders to inspect, challenge, and revise plans if they conflict with clinical…
CoPlan: A Trustworthy Co-Intelligence Interface for Care Planning through Role-Based Contestable Argument Graphs
The paper introduces CoPlan, an AI system designed to assist in care planning by allowing multiple stakeholders (clinicians, patients, etc.) to inspect, challenge, and revise plans. It uses a multi-agent workflow where…
Page 13 of 47
