All notes, newest first
2,343 notes. Notes 1,251 to 1,300, page 26 of 47.
CAVA: Canonical Action Verification and Attestation for Runtime Governance of Agentic AI Systems
The paper presents Canonical Action Verification and Attestation (CAVA), a system that converts various runtime actions of agentic AI systems into standardized action objects, aiming to address the challenge of…
Deep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning Models
Researchers propose a new method called Deep Interaction to correct errors made by large language models (LLMs) during complex, multi-step tasks. The method allows for direct editing of the original response, improving…
Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0
The research evaluates if improvements from agent-optimization methods can stack up over time in a continual learning setting. Three optimizer-driven methods (GEPA, Meta Harness, and RELAI's Verifiable Continual…
Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0
Researchers investigated if improvements made by agent-optimization methods persist when agents are optimized again on new tasks. They found that one method called RELAI-VCL was the only one that both transferred…
Early Adoption of Agentic Coding Tools by GitHub Projects
The paper investigates the early adoption of automated coding tools by GitHub projects. It found that while intensive adoption is concentrated in a few projects, smaller projects tend to have higher participation…
Early Adoption of Agentic Coding Tools by GitHub Projects
The paper investigates the adoption and management of agentic coding tools in GitHub projects. It reveals that while some projects have intensive adoption, most generate only a few agentic pull requests per three…
Early Adoption of Agentic Coding Tools by GitHub Projects
This research investigates the adoption and management of agentic coding tools in software development on GitHub. The study analyzes 25,264 agentic pull requests from 2,361 popular repositories to understand (1) how…
Earthquaker-AI: A Retrieval-Augmented Generation Framework with Rubric-Based Assessment for Primary School Earthquake Education
The paper introduces Earthquaker-AI, a hybrid educational framework that combines conversational AI with Lego robotics to teach primary school students about earthquake preparedness. The system uses Lego WeDo2 for…
Earthquaker-AI: A Retrieval-Augmented Generation Framework with Rubric-Based Assessment for Primary School Earthquake Education
The paper introduces Earthquaker-AI, a hybrid educational framework that uses Lego WeDo2 robotics for earthquake simulations and an AI assistant for guided learning and feedback. The system aims to enhance earthquake…
Experience Memory Graph: One-Shot Error Correction for Agents
Researchers propose a new framework called Experience Memory Graph (EMG) to help large language model agents recover from failures more effectively in complex, long-horizon tasks. Instead of using prompt-based…
Experience Memory Graph: One-Shot Error Correction for Agents
The researchers propose a new framework called Experience Memory Graph (EMG) to help large language model agents recover from failures more effectively in complex, long-horizon tasks. EMG reformulates failure recovery…
Explaining Reinforcement Learning Agents via Inductive Logic Programming
This research aims to improve Reinforcement Learning (RL) policies by making them more transparent and interpretable. It proposes objective and planning-oriented metrics for policy explainability in RL settings using…
Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code
Researchers introduce 'generative compilation', an approach that allows compilers to provide feedback on partial programs during the generation of AI-generated code in languages with rich static semantics like Rust…
Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code
Researchers introduce 'generative compilation', an approach to get feedback from compilers on partially generated code during the code generation process. The method aims to reduce errors and improve the functionality…
Groc-PO: Grounded Context Preference Optimization for Truthful Multimodal LLMs
Researchers propose a new method called Grounded Context Preference Optimization (Groc-PO) to improve the truthfulness and utility of Multimodal Large Language Models (MLLMs). Current MLLMs often make errors due to…
How Agents Ask for Permission: User Permissions for AI Agents, from Interfaces to Enforcement
The authors of this research paper review 21 proposals for agent permissions systems in AI, focusing on user-level permissions policies. They also analyze five commercial agents and compare their permissions handling…
How Agents Ask for Permission: User Permissions for AI Agents, from Interfaces to Enforcement
This research paper discusses the importance of user-level permissions for AI agents to protect users from risks such as data leaks and unauthorized actions. The authors survey 21 proposals for agent permissions…
Improving Wind and Solar Power Prediction with Efficient Wrapper-based Feature Selection: An Empirical Study
Researchers propose a new method for feature selection in renewable energy prediction pipelines, called Cluster-based Sequential Feature Selection (CSFS). This method aims to address the gap in limited or unsystematic…
Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents
The paper proposes a new framework called Memory as a Controlled Process (MemCon) for large language model (LLM) agents that use external memory systems. MemCon learns an online policy to adaptively decide when, what…
Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents
The paper presents a new framework called Memory as a Controlled Process (MemCon) for large language model (LLM) agents. MemCon aims to address the limitation of existing memory systems that rely on fixed…
Multi-Expert Routing for Multi-Domain Low-Resource OCR: A Manchu Case Study
The paper introduces a multi-expert system for Optical Character Recognition (OCR) of historical Manchu texts which have various writing styles and limited labeled data. The system uses a router that classifies pages…
Partially Correlated Verifier Cascades in LLM Harnesses: Concave Log-Odds, Polynomial Reliability, and Blind-Spot Ceilings
The text presents a new theory for partially correlated verifier cascades in LLM harnesses (a system used to verify candidate answers). The theory provides insights into the growth and decay of failure rates, the…
Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation
The paper proposes a new approach to penetration testing for AI-enabled systems, focusing on evaluating whether adversaries can manipulate system behavior without directly compromising the underlying infrastructure…
Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation
The paper by Allahbakhsh et al. proposes a new approach to penetration testing for AI-enabled systems, focusing on behavioral objective violation instead of traditional resource compromise. The authors argue that…
Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation
The authors propose a new approach to penetration testing for AI-enabled systems. Instead of focusing on direct compromises of infrastructure, they suggest evaluating if adversaries can manipulate system behavior…
SAFETY SENTRY: Context-Aware Human Intervention via EXECUTE-ASK-REFUSE Routing
Researchers present Safety Sentry, a lightweight guard model that makes decisions about executing, asking for help, or refusing actions in real-world environments. This model aims to improve safety and autonomy by…
Social Simulations: from Agent-Based Modeling to Digital Twins
The text discusses the evolution of social simulation from traditional agent-based modeling to more advanced AI-enhanced simulations and Social Digital Twins, focusing on their methodological foundations, applications…
Social Simulations: from Agent-Based Modeling to Digital Twins
The text discusses the evolution of social simulation, moving from traditional agent-based models with explicitly defined rules to more advanced simulations using Large Language Models and Social Digital Twins. It…
STOCKTAKE: Measuring the Gap Between Perception and Action in LLM Agents with a Fair Oracle
Researchers introduce a new benchmark called STOCKTAKE for evaluating LLM agents in supply-chain replenishment tasks over 26 weeks. The benchmark separates state estimation and control, measures the agent's ability to…
The Dynamic Verifiable Multi-Agent Human Agentic Loyalty Loop (DVM-HALL) Model and the Net Human-Agent Score (NHAS) in Autonomous Commerce
The paper introduces a new model called Dynamic Verifiable Multi-Agent Human Agentic Loyalty Loop (DVM-HALL) and a metric called Net Human-Agent Score (NHAS). These tools are designed to help brands adapt to the…
The Dynamic Verifiable Multi-Agent Human Agentic Loyalty Loop (DVM-HALL) Model and the Net Human-Agent Score (NHAS) in Autonomous Commerce
The Dynamic Verifiable Multi-Agent Human Agentic Loyalty Loop (DVM-HALL) model is introduced in this research, aiming to account for the effects of autonomous AI agents on traditional customer loyalty paradigms. The…
The Dynamic Verifiable Multi-Agent Human Agentic Loyalty Loop (DVM-HALL) Model and the Net Human-Agent Score (NHAS) in Autonomous Commerce
The authors present a new model called Dynamic Verifiable Multi-Agent Human Agentic Loyalty Loop (DVM-HALL) and the Net Human-Agent Score (NHAS). This model aims to account for the changing customer loyalty paradigms…
Traffic-Aware Randomized Smoothing for LLM-Based Network Intrusion Detection
The paper introduces Traffic-Aware Randomized Smoothing (TA-RS), a defense mechanism for Large Language Model (LLM)-based intrusion detection systems to enhance their robustness against feasible traffic manipulation…
Transforming Rank: How Architecture Navigates the Spectral Pathologies of Depth
The research investigates how the design of Transformer feedforward block architecture affects the preservation of 'rank' (a mathematical concept related to the expressiveness of a network) across depth during…
UESF-Bench: Benchmarking and Probing for Unified Embodied Seeking and Following
The authors introduce the Unified Embodied Seeking and Following Benchmark (UESF-Bench), a new benchmark for embodied agents that allows them to search for and follow language-described targets in dynamic environments…
UESF-Bench: Benchmarking and Probing for Unified Embodied Seeking and Following
Researchers have introduced UESF-Bench, a new benchmark to evaluate the performance of AI agents in language-guided human following tasks. The current benchmarks assume that the target person is visible at the start of…
Unleashing Multimodal Large Language Models for Training-free HOI Detection in the Wild
The paper presents a new framework called AgentHOI that uses large language models to detect human-object interactions in complex scenes without needing any specific training data. It focuses on open-ended semantic…
Unleashing Multimodal Large Language Models for Training-free HOI Detection in the Wild
The paper presents a new framework called AgentHOI that uses multimodal large language models (MLLMs) to detect human-object interactions (HOIs) in complex scenes without the need for any HOI data during training. The…
UTS at ELOQUENT 2026 Voight-Kampff: structural shifts in AI writing bypass state-of-the-art detectors
The authors investigate language model evasion attacks on state-of-the-art detectors in the ELOQUENT 2026 Voight-Kampff competition. They find that pushing generated text out of the detector's training distribution…
When Bots Join the Team: Bot Adoption and the Institutional Fabric of Open-Source Software Projects
The study examines how the adoption of bots in open-source software projects affects group organization and collaboration. The research finds that bot adoption leads to increased repeated collaboration, recognition of…
When Bots Join the Team: Bot Adoption and the Institutional Fabric of Open-Source Software Projects
Researchers studied the impact of AI bots joining human teams in open-source software projects. They found that bot adoption leads to more repeated collaboration, less conflict, and more distinctive outputs. However…
A Learning-Rate-Gated Failure of GRPO in a Small Language and Vision-Language Model Web Agent: A Controlled Null and Its Mechanism
The study investigates the impact of Reinforcement learning with verifiable rewards and Group Relative Policy Optimization (GRPO) on a small language and vision-language model web agent. The research found that GRPO…
A Learning-Rate-Gated Failure of GRPO in a Small Language and Vision-Language Model Web Agent: A Controlled Null and Its Mechanism
The research investigates the effectiveness of Reinforcement learning with verifiable rewards and Group Relative Policy Optimization (GRPO) on a small language and vision-language model web agent at scales ranging from…
A Multi-Agent System for Autonomous, Fine-Tuning-Free Clinical Symptom Detection: Development and Validation Study
A new multi-agent system named Pythia was developed for automatically and independently creating and optimizing clinical concept extraction prompts without manual engineering or fine-tuning. The study compared Pythia…
A Multi-Agent System for Autonomous, Fine-Tuning-Free Clinical Symptom Detection: Development and Validation Study
Researchers present Pythia, a multi-agent system that automatically generates and optimizes extraction prompts for clinical concepts without manual engineering or fine-tuning. They compare Pythia with a curated lexicon…
A Multi-Agent System for Autonomous, Fine-Tuning-Free Clinical Symptom Detection: Development and Validation Study
A new system called Pythia was developed, which automatically generates and optimizes extraction prompts for clinical concepts without the need for manual prompt engineering or fine-tuning. The researchers compared…
Agentic Service-Oriented Computing: A Manifesto for the Next Frontier of Service-Oriented Computing
The text discusses a new research area called Agentic Service-Oriented Computing (ASOC), which focuses on engineering agents as services, managing their complex distributed workflows, and ensuring their reliability for…
Agentic Service-Oriented Computing: A Manifesto for the Next Frontier of Service-Oriented Computing
The paper introduces Agentic Service-Oriented Computing (ASOC), a new research area focusing on engineering agents as services, orchestrating services through autonomous and semi-autonomous agents, and governing…
Atomic Units of X: The Compression Layer of Intelligence
The paper proposes a theoretical framework that views intelligence as a process of compressing complex phenomena into reusable atomic units. This is supported by evidence from various fields, including cognitive…
Audio-Native Speech Recognition with a Frozen Discrete-Diffusion Language Model
Researchers train a discrete diffusion language model to transcribe speech instead of using autoregressive decoders that emit one token at a time. The model is based on a mixture-of-experts called DiffusionGemma, and…
Page 26 of 47
