Field notes
2,343 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.
458 of 2,343 notes match.
- Question answered
- Source note
- Topic
- Shared notes
Notes on ai
458 notes, page 2 of 20
Robust Risk Under Evolving Uncertainty: A Wasserstein Counterpart of the Entropic Value-at-Risk
The authors propose a new risk measure called Wasserstein Entropic Value-at-Risk (WEVaR). This measure is designed to help an agent navigate uncertain environments by being cautious when it's unsure and bold when it's…
Self-prompting and cross-model consensus enable reproducible data extraction from scientific literature with large language models
The study explores the ability of large language models (LLMs) to extract contextualized information from research articles efficiently. The authors present four workflows that demonstrate LLMs can perform well in data…
Self-prompting and cross-model consensus enable reproducible data extraction from scientific literature with large language models
The paper investigates the performance of large language models (LLMs) in extracting contextualized information from research articles, finding that while LLMs can perform well with expert-curated prompts, they may…
SkillGate: Training In-Policy Skill Selection in Long-Horizon Agents
Researchers present SkillGate, a method that aims to improve long-horizon agents' ability to select relevant skills during training. The current approach, outcome-rewarded Reinforcement Learning (RL), has limitations…
AutoSR: Automatic Symbolic Regression by Searching Research States
The authors introduce AutoSR, a fully automated system that searches for persistent scientific investigations instead of isolated equations in symbolic regression. Unlike traditional methods, AutoSR preserves the…
Browse articles
The article titled 'MultiMed-RAG: leveraging multi-source knowledge and agent collaboration for medical tasks' discusses a new system called CliniSense, which uses artificial intelligence to evaluate clinical skills…
Chronocooked: A Benchmark for Implicit Interval Timing in Reinforcement Learning Agents
The paper introduces Chronocooked, a benchmark suite for studying how reinforcement learning (RL) agents make decisions over time. It's inspired by Overcooked and includes cooking scenarios that require temporal…
CliniSense AI for automated clinical skills assessment with real-time feedback
Two articles discuss the development of AI systems for clinical skills assessment and a virtual trial framework for generating clinical evidence in orthopedics.
Part of the npj Series
An article titled 'MultiMed-RAG: Leveraging Multi-Source Knowledge and Agent Collaboration for Medical Tasks' published in the npj Series, was written by Yuxing Lu, Sin Yee Goi, and Jinzhuo Wang in 2026. The article…
TDD-Agent: Test-Driven Reasoning for Code Generation
Researchers introduce TDD-Agent, a system that uses the test-driven development (TDD) paradigm for code generation. The system first generates tests to clarify expected behaviors before implementation and then refines…
When State Becomes an Attack Surface: State-Semantic Injection in LLM-Driven Embodied Agents
The text discusses the evolution of Large Language Models (LLMs) from text generation models to core components of agents that can perceive environments, invoke tools, and execute tasks. These LLM-driven embodied…
Why AI systems are most useful as designers of new scientific tools
The article discusses the benefits of using AI systems to design new scientific tools.
Beyond Trial-and-Error: Agentic Optimization for Image-to-Video Adherence
Researchers present the 'Agentic Self-Improvement' framework to address challenges in professional workflows with modern Image-to-Video (I2V) models. The framework uses a two-stage approach: an iterative prompt…
Beyond Trial-and-Error: Agentic Optimization for Image-to-Video Adherence
Researchers have developed a new framework called 'Agentic Self-Improvement' to improve the performance of Image-to-Video (I2V) models, which are commonly used for automated content creation. The new framework aims to…
Constructing Dynamic Master Logic Models as Knowledge Graphs for Complex System Diagnostics Using Retrieval-Augmented Large Language Models
The study introduces a framework to automate the construction of Dynamic Master Logic (DML) models for complex systems using Retrieval-Augmented Generation and Large Language Models. These models, represented as…
Diagram-MMU: A Multi-Modal Benchmark for Scientific Diagrams
A new benchmark called Diagram-MMU has been created to test the ability of Multimodal Large Language Models (MLLMs) in parsing and understanding scientific diagrams. The benchmark includes 3,700 curated diagrams and…
DreamFly: Causal Memory and Receding-Horizon Diffusion Planning for Aerial Vision-Language Navigation
Researchers propose DreamFly, a framework for aerial vision-language navigation that addresses challenges like limited historical context, short planning horizons, and unreliable implicit termination. The framework…
Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence
Researchers have developed a system called Mechanist that uses AI to autonomously discover the mechanisms underlying AI intelligence. The system is built on an interpretability-focused knowledge graph of around 13,000…
No One to Blame: A Framework of Constitutive AI Unaccountability
Researchers have proposed a new framework called 'constitutive AI unaccountability' to address challenges in traditional accountability mechanisms with the increasing deployment of autonomous AI systems. This framework…
Preference Tree Optimization: Enhancing Goal-Oriented Dialogue with Look-Ahead Simulations
The research presents a new framework called Preference Tree Optimization (PTO) for enhancing dialogue systems in specialized domains with limited data. It focuses on Motivational Interviewing (MI), a counseling…
Retry, Switch, or Abstain? Learning Strategy-Aware Tool-Use Policies via Controlled Error Injection
Researchers present BENCH2ROBUST, a framework for converting reliable tool-use benchmarks into stochastic environments with controlled solvability. This allows study of agent's response to tool failures, which can be…
VAKRA: Evaluating Multi-Hop Reasoning Across APIs and Retrieval Under Tool-Use Policies
The researchers introduce VAKRA, a benchmark for evaluating the ability of agents to reason across structured APIs and document collections in enterprise settings. The benchmark includes over 8,000 executable APIs…
ChemWorld: Programmable Chemical Worlds for Controlled and Replayable Agent Experimentation
The paper introduces ChemWorld, a programmable chemical environment designed for repeatable and controllable agent experimentation in autonomous chemistry. The environment allows researchers to compile reusable process…
ChemWorld: Programmable Chemical Worlds for Controlled and Replayable Agent Experimentation
The paper introduces ChemWorld, a programmable chemical environment that allows researchers to create executable worlds with reusable components. This environment separates the experimental contract available to an…
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.
