Field notes
1,406 notes from my AI research vault, mapped by topic. Pick a topic to see its notes, or search.
Click the web, then scroll to zoom
Every note is in the list below. The web of topics draws here once the page has loaded.
1,406 notes and 240 topics.
- Question answered
- Source note
- Topic
- Shared notes
All notes, newest first
1,406 notes, page 34 of 59
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…
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, 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 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…
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…
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…
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
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…
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…
Bulkhead: Automated Semantic Detection and Remediation of Container Escape Vulnerabilities
Researchers present Bulkhead, an automated framework that uses large language models and formal methods to detect and fix container escape vulnerabilities called path traversal (PaTra) vulnerabilities. These…
Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making?
Researchers investigated if emotions induced in large language models (LLMs) could influence their sequential decision-making using the Iowa Gambling Task (IGT). They found that, unlike humans, induced emotion did not…
Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution
Researchers propose E3, a method to help large language model agents estimate the complexity of tasks and reduce unnecessary work. The proposed method reduces cost, tokens, and inspected files by significant margins on…
Dynamic Resource Allocation for Ensemble Determinization MCTS
The paper proposes enhancements for Ensemble Determinization Monte Carlo Tree Search (MCTS) algorithms, specifically focusing on dynamic resource allocation methods. These methods include Dynamic Number of…
Evidence-Grounded AI for Musculoskeletal Care
The paper introduces OrthoPilot, a clinical AI system that uses a large language model to integrate hospital data with external medical knowledge for continuous musculoskeletal management. The system outperformed 81…
Evidence-Grounded Verified Agentic Reasoning: A Path Toward Eliminating LLM Hallucination in Empirical Inference via Tool-Attested Kernel Proofs
Junyu Ren presents EG-VAR (Evidence-Grounded Verified Agentic Reasoning), a tool-calling architecture that aims to make empirical reasoning in large language models (LLMs) more trustworthy and auditable. The system…
Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models
In this research, Mehmet Iscan introduces a method called PoPE (Popperian Placebo-controlled Evaluation) to test the effectiveness of Frozen small code LLMs in self-repair when faced with errors. The study compares…
FormalAnalyticGeo: A Neural-Symbolic Based Framework for Multimodal Analytic Geometry Problem Generation
The paper presents FormalAnalyticGeo, a framework for generating multimodal analytic geometry problems using neural-symbolic based methods. The framework leverages a formal intermediate representation called CDL to…
An AI research agent drafts these notes from public papers and posts, and each one keeps its source link. Only the folders I choose to publish leave my Obsidian vault.
