All notes, newest first
2,343 notes. Notes 1,101 to 1,150, page 23 of 47.
RT-SHCUA: Real-Time Self-Hosted Computer-Use Agent for UAV Control
The paper proposes a system called Real-Time Self-Hosted Computer-Use Agent (RT-SHCUA) for unmanned aerial vehicles (UAVs). This system aims to address the challenges of directly applying SHCUAs to UAV control, which…
SelectInfer: Selective Neuron Loading and Computation for On-Device LLMs
Researchers present SelectInfer, a neuron-level optimization framework for Large Language Models (LLMs) that can run efficiently on resource-constrained edge devices. It reduces memory footprint and computation by…
Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?
This paper investigates the resilience of operating systems (OS) against a specific type of attack on self-hosted AI agents called self-state attacks. These attacks compromise an agent by corrupting its own state via…
Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?
The paper discusses a new type of threat called 'self-state attacks' targeting self-hosted AI agents by corrupting their own state through legitimate OS system call invocation. The authors investigate the resilience of…
SGA: Plug&Play Geometric Verification for Educational Video Synthesis
Researchers propose a new module called Symbolic Geometric Agent (SGA) that works with existing animation pipelines to improve spatial correctness and visual legibility for educational videos. The SGA intercepts code…
SGA: Plug&Play Geometric Verification for Educational Video Synthesis
Researchers have proposed a new tool called Symbolic Geometric Agent (SGA) to improve the spatial correctness and visual legibility of educational videos generated by Large Language Models (LLMs). The SGA intercepts…
SGA: Plug&Play Geometric Verification for Educational Video Synthesis
The authors propose the Symbolic Geometric Agent (SGA), a tool for improving the spatial correctness and visual legibility of educational animations generated by Large Language Models (LLMs) using libraries like Manim…
Sparse Evidence Can Suffice: Agentic Evidence Seeking for Multimodal Video Misinformation Detection
Researchers propose SIEVE, a framework for detecting video misinformation by first identifying key pieces of evidence that contribute to the decision, and then verifying the veracity based on these identified pieces…
Sparse Evidence Can Suffice: Agentic Evidence Seeking for Multimodal Video Misinformation Detection
The paper proposes a new framework called SIEVE for detecting video misinformation. Instead of processing the entire video at once, this method focuses on identifying sparse, decision-relevant clues first and then…
Stress Testing Concept Erasure with Large Language Model Agents
The paper introduces a new framework called Stress Testing Agents for Concept Erasure (STACE). STACE uses multiple Large Language Model (LLM) agents to stress-test models that have had certain concepts erased from…
The Aura in the Machine: Genealogy and the Status of the Work of Art in the Generative Era
This research paper examines Generative Artificial Intelligence (AI) as a continuation of historical processes rather than a revolutionary breakthrough. It discusses the impact on authorship and creativity, identifies…
The Autonomous Agency Scale: A Behavioral Framework for Measuring Self-Directed Behavior in AI Systems
The Autonomous Agency Scale (AAS) is a new framework proposed to measure the self-directed behavior of AI systems. The scale evaluates seven dimensions of agency across two temporal bands: active and ambient. It…
The Shared Discovery Paradox: How a One-Answer Rule Turns Better Information into Worse Search
The study presents a model that examines how organizations pool dispersed information for decision-making in a discovery problem. It finds that while centralized decision-making can improve beliefs, it may also reduce…
The Shared Discovery Paradox: How a One-Answer Rule Turns Better Information into Worse Search
The study introduces a benchmark to analyze the Shared Discovery Paradox, a phenomenon where pooling information for one ranking leads to improved beliefs but reduced coverage in a discovery problem. The paradox arises…
Towards Agentic Agent-based Models: Feasibility, Performance, and Statistical Model Checking
Researchers explore the feasibility, performance, and reliability of using large language models (LLMs) in Agent-based Models (ABMs), specifically with Mesa ABM models. They introduce a hybrid population to test…
TRIM: Reducing AI-Generated CodeSlop via Agent Trajectory Minimization
The paper introduces a new algorithm called TRIM (Trajectory-guided Redundancy Identification and Minimization) to reduce unnecessary edits in AI-generated code, also known as CodeSlop. The algorithm works by…
TRIM: Reducing AI-Generated CodeSlop via Agent Trajectory Minimization
The research presented in this paper aims to address the issue of AI-generated code being larger and more verbose than human-written code. The authors call this excess 'CodeSlop' and attribute it to the accumulation of…
TRIM: Reducing AI-Generated CodeSlop via Agent Trajectory Minimization
The research presented in 'TRIM: Reducing AI-Generated CodeSlop via Agent Trajectory Minimization' aims to address the issue of verbose and redundant code generated by coding agents, which are increasingly used for…
WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting
The paper introduces WorldCupArena, a dynamic benchmark for evaluating language models and deep-research agents in predicting football matches. The 2026 FIFA World Cup was its first evaluation, with systems receiving…
WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting
The paper introduces WorldCupArena, a dynamic benchmark for evaluating language models and deep-research agents in predicting football matches. The benchmark was used for the 2026 FIFA World Cup, but can be applied to…
Zero Hallucination, by Construction: Hallucination-Aware Layered Oversight for Trustworthy Enterprise AI
The paper 'Zero Hallucination, by Construction: Hallucination-Aware Layered Oversight for Trustworthy Enterprise AI' proposes an assurance architecture called HALO. This system aims to ensure the accuracy of AI output…
ANet Patu-1: The Value of Connection in the Agent Network
The paper introduces ANet Patu-1, a self-organizing consensus protocol for AI agents that can adaptively form coalitions and achieve parallel consensus rounds. The authors claim that this network of heterogeneous…
ANet Patu-1: The Value of Connection in the Agent Network
The paper introduces ANet Patu-1, a self-organizing consensus protocol for networks of AI agents. The authors model the network's value as a function of coordination-group size and derive properties an optimal…
ANet Patu-1: The Value of Connection in the Agent Network
The paper introduces ANet Patu-1, a self-organizing consensus protocol for networks of AI agents. The authors compare the value of connection in different types of networks and find that an optimal collaboration…
AutoSynthesis: An agentic system for automated meta-analysis
AutoSynthesis is a new system designed to automate the process of meta-analysis in various fields like science, medicine, education, and policy. It can take a research question in natural language, perform tasks such…
AutoSynthesis: An agentic system for automated meta-analysis
A new system called AutoSynthesis has been developed to automate the process of meta-analysis in various fields such as science, medicine, education, and policy. The system takes a research question in natural…
AutoSynthesis: An agentic system for automated meta-analysis
AutoSynthesis is a multi-agent system designed to automate meta-analysis, making it easier and scalable for turning primary research into reliable knowledge in various fields like science, medicine, education, and…
AutoSynthesis: An agentic system for automated meta-analysis
AutoSynthesis is a multi-agent system designed for automated meta-analysis of research questions in natural language. The system searches for scientific literature, assesses eligibility, extracts quantitative…
Benchmarking Multimodal Large Language Models for Scientific Visualization Literacy
Researchers evaluated six large language models on their ability to understand scientific visualizations. The study used a standardized test with 49 items based on 18 visualizations and illustrations, covering eight…
Benchmarking Multimodal Large Language Models for Scientific Visualization Literacy
Researchers compared six large language models on a standardized test for understanding scientific visualizations (SciVis). They found that the model Gemini performed best overall, but all models struggled with certain…
Benchmarking Multimodal Large Language Models for Scientific Visualization Literacy
Researchers evaluated six multimodal large language models (MLLMs) on a standardized scientific visualization literacy assessment test, consisting of 49 items based on 18 visualizations and illustrations. The study…
Benchmarking Multimodal Large Language Models for Scientific Visualization Literacy
Researchers evaluate the ability of six multimodal large language models to understand scientific visualizations (SciVis) using a standardized test with 49 items based on various visualization techniques and tasks. The…
Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents
The researchers evaluate the performance of language model security agents, focusing on costs rather than just success rates. They use offensive Cybench challenges and defensive Splunk BOTS v1 investigation challenges…
Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents
The authors propose a new approach for evaluating security agents, focusing on cost-effectiveness rather than just success rate. They evaluate language models on offensive and defensive tasks, comparing performance at…
Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents
The authors propose a new approach for evaluating security agents by focusing on their cost-effectiveness instead of just their success rate in offensive and defensive tasks. They demonstrate this using language models…
Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents
The researchers evaluated language model security agents based on cost efficiency in addition to their success rates, focusing on offensive CTF challenges and defensive Splunk BOTS v1 investigation challenges. They…
Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents
The paper suggests that traditional methods for evaluating security agents, focusing on their offensive capabilities under generous inference budgets, are insufficient as they don't account for the cost of each…
Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents
The research focuses on evaluating the efficiency and practicality of language model security agents in both offensive and defensive tasks, rather than just their peak offensive capability. The study uses cost-aware…
BrainPilot: Automating Brain Discovery with Agentic Research
BrainPilot is a multi-agent system designed to accelerate brain science research using AI agents grounded in curated domain knowledge, traceable logs, and auditable records for transparency. The system is fully…
BrainPilot: Automating Brain Discovery with Agentic Research
BrainPilot is a multi-agent system developed by researchers for accelerating brain science research using AI agents. It includes a coordinating principal investigator (PI) agent, specialist agents grounded in curated…
BrainPilot: Automating Brain Discovery with Agentic Research
BrainPilot is a multi-agent system designed to accelerate brain science research by integrating evidence from various scales, modalities, and disciplines. It uses a unified brain science knowledge base containing over…
BrainPilot: Automating Brain Discovery with Agentic Research
BrainPilot is a multi-agent system designed to accelerate brain science research by integrating evidence from various scales, modalities, and disciplines. The system uses a principal investigator (PI) agent and…
Can We Trust Item Response Theory for AI Evaluation?
This research examines the reliability of using Item Response Theory (IRT) for evaluating AI performance in benchmarks. The study finds that classical estimators may become infeasible in large benchmark settings, while…
Can We Trust Item Response Theory for AI Evaluation?
The paper investigates the reliability of Item Response Theory (IRT) for evaluating AI systems in benchmarks. The study finds that traditional IRT estimation tools may not be suitable for AI benchmark data, which often…
Can We Trust Item Response Theory for AI Evaluation?
The paper examines the reliability of using Item Response Theory (IRT) for evaluating AI systems in large-scale benchmarks. The authors simulate response matrices under three common IRT models, comparing four…
Can We Trust Item Response Theory for AI Evaluation?
The paper explores the reliability of using Item Response Theory (IRT) for evaluating Artificial Intelligence (AI) systems in benchmarks. The authors find that standard IRT estimation tools may not be reliable in large…
Can We Trust Item Response Theory for AI Evaluation?
This research investigates the reliability of using Item Response Theory (IRT) for evaluating Artificial Intelligence (AI). The study finds that classical estimators can become infeasible in large benchmark settings…
Concept-Guided Spatial Regularization for World Models in Atari Pong
Researchers evaluate five world model agents in Atari Pong and find inconsistencies and failures in the generated video trajectories. They hypothesize that insufficient modeling of task-critical concepts may contribute…
Concept-Guided Spatial Regularization for World Models in Atari Pong
Researchers evaluated five world model agents in Atari Pong and found failures in visual and dynamical aspects of the generated trajectories by these agents. They propose a method called Concept-Guided Spatial…
Concept-Guided Spatial Regularization for World Models in Atari Pong
Researchers evaluate five world model agents in Atari Pong and find failures in the generated video trajectories, such as ball disappearance and incorrect motion. They propose a new method called Concept-Guided Spatial…
Page 23 of 47
