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 49 of 59
ManimAgent: Self-Evolving Multimodal Agents for Visual Education
The research presents ManimAgent, a self-evolving multimodal agent that learns from its failures and successes in generating Python code using the Manim library to render mathematical animations. The agent stores these…
MCP Server Architecture Patterns for LLM-Integrated Applications
This industry experience paper presents five architectural patterns observed in the use of Model Context Protocol (MCP) servers, which connect large language models to external tools, data sources, and services. The…
MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems
The paper presents Mesa, a framework for prioritizing vulnerable communication channels in multi-agent systems (MAS). Mesa uses graph-theoretic metrics and dynamic probes to identify the edges most likely to affect the…
Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms
This research presents a theoretical framework that explains why certain 'discarded' norms in contrastive embedding models, which were thought to be ignored during training, actually correlate with semantic properties…
PromptGNN-sim: Deep Fusion and Alignment of GNN and LLMs for Text-Attributed Graph Learning
Researchers propose a new framework called PromptGNN-sim to improve the performance of Text-Attributed Graph Learning tasks. The method combines Graph Attention Network (GAT) and Language Model (LLM) in a…
Rehearsed Multi-Agent Live Product Demonstrations with Real-Time Voice Question Answering
The authors propose Rhetor, a multi-agent system that automates live product demonstrations by merging UI exploration and source-code analysis, producing rehearsed demos with synchronized narration and real-time voice…
Retrieval Backward Attention without Additional Training: Enhance Embeddings of Large Language Models via Repetition
Researchers propose a method called ReBA (Retrieval Backward Attention) to enhance the quality of word-level embeddings produced by pretrained language models without affecting sentence-level representations…
Self-Evolving World Models for LLM Agent Planning
In this paper, the authors introduce WorldEvolver, a framework for self-evolving world models designed to improve the planning abilities of long-horizon language model agents by offering predictions of action…
Sequential Fairness Auditing with Limited Output Access
This research proposes a new method for auditing AI systems for fairness in real-world scenarios where auditors have limited access to deployed models. The method is a tolerance-aware sequential hypothesis-testing…
SIMAX: A Scalable and Interpretable Framework for Multi-Fidelity and Annotated Clinician-Patient Dialogue Simulation
The study introduces SIMAX, a framework that generates controlled clinical dialogue data with reference behavioral annotations for evaluating AI-driven communication coding systems. The generated dialogues are of…
Symbiotic Cooperation for Web Agents: Harnessing Complementary Strengths of Large and Small LLMs
Researchers propose AgentSymbiotic, an iterative framework that enhances both large and small Language Model (LLM) performance in web browsing tasks by combining data synthesis with task-performance. Large LLMs…
The FIL Hypothesis: Inductive Biases Help with Kernel Engineering
A study suggests that for AI applications in science and the physical world, there's a fundamental scaling limit due to long Feedback Information Loops (FIL). The proposed solution is an orthogonal method based on…
The Human Creativity Benchmark
The authors propose a new benchmark for evaluating creative AI called the Human Creativity Benchmark (HCB). This benchmark separates two signals of creativity, convergence and divergence, by collecting preferences…
To Tab or Not to Tab: Measuring Critical Engagement in AI Code Completion Tools Using Behavioral Signals and Attention Checks
Researchers have developed a new code completion tool called Clover to help students write programs using AI suggestions. The tool logs interactions with the suggestions and offers attention checks to encourage…
Towards Continual Motion-Language Agents: LoRA Variants for Incremental Motion Understanding and Generation
The paper presents a new method to create motion-language agents that can understand and generate human movements in dynamic environments without forgetting previously acquired skills. The method, called LoRA variants…
TRACE: Temporal Relationship-Aware Conversational Entrainment Detection in Dyadic Speech
Researchers introduce a dataset (DyadEE) for studying emotional entrainment in dyadic speech interactions, including both entrained and disrupted conversations. They also propose TRACE, a new framework that models…
TraceLab: Characterizing Coding Agent Workloads for LLM Serving
Researchers collect and release a dataset of approximately 4,300 coding-agent sessions from their own use of Claude Code and Codex. The data shows that coding-agent workloads feature long autonomous loops, long…
Translating Natural Language to Strategic Temporal Specifications via LLMs
Researchers have developed a framework for translating Natural Language descriptions of strategic requirements into well-formed ATL/ATL* formulas using Large Language Models (LLMs). They created and validated a novel…
Using Large Language Models as Low-Cost Statistical Estimators for Human-Response Data
A study proposes using large language models (LLMs) as a cheaper alternative to human subject experiments for quantitative research in social and behavioral sciences. The LLM is shown to estimate conditional…
VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes
Researchers present a method to learn humanoid locomotion and manipulation tasks by synthetically generating vision-language-kinematics (VLK) supervision in reconstructed scenes. They produce 48,000 paired trajectories…
Whose Side Is Your Agent On? Multi-Party Principal Loyalty in LLM Agents
In a rapidly growing field of artificial intelligence agents, there is a need to ensure that these agents remain loyal to the principal they represent while also engaging with a counterparty whose interests may…
Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection
In this research, the authors investigate how Large Language Models (LLMs) used for automated vulnerability detection in code are influenced by cognitive biases similar to those that affect human judgment. They present…
CToolEval: A Chinese Benchmark for LLM-Powered Agent Evaluation in Real-World API Interactions
The authors propose CToolEval, a benchmark for evaluating the performance of large language models as agents in real-world Chinese API interactions. The benchmark includes 398 APIs from various apps and covers 14…
AU-Harness: An Open-Source Toolkit for Holistic Evaluation of AudioLLMs
The authors introduce AU-Harness, an efficient and comprehensive evaluation framework for Large Audio Language Models (LALMs). The system addresses limitations in existing toolkits by improving speed, providing…
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.
