AI Agents

Moody’s Integrates AI Agents With Anthropic’s Claude

Started a video series on building an orchestration layer for LLM post-training [P]

Hi everyone! Context, motivation, a lot of yapping, feel free to skip to TL;DR. A while back I posted here asking [D] What framework do y...

Sierra's Bret Taylor says the era of clicking buttons is over | TechCrunch

Co-founder of Sierra predicts that AI agents will make software interfaces obsolete.

Artificial Intelligence in corporate communication: Transformational tool or existential threat?

The article explores the impact of Artificial Intelligence on corporate communication, assessing its potential as both a transformative t...

[2602.11897] Agentic AI for Cybersecurity: A Meta-Cognitive Architecture for Governable Autonomy

This paper presents a novel meta-cognitive architecture for AI in cybersecurity, advocating for a shift from traditional model-centric sy...

[2511.14624] Active Matter as a framework for living systems-inspired Robophysics

This article explores the intersection of active matter physics and robotics, focusing on the challenges faced by bio-inspired robotic sy...

[2510.19692] Toward Agentic Software Engineering Beyond Code: Framing Vision, Values, and Vocabulary

This article discusses the emerging field of agentic software engineering, emphasizing the need to expand its focus beyond code to encomp...

[2510.10509] MARS-Sep: Multimodal-Aligned Reinforced Sound Separation

The paper presents MARS-Sep, a novel reinforcement learning framework for sound separation that enhances semantic consistency by aligning...

[2510.02001] Generating Findings for Jaw Cysts in Dental Panoramic Radiographs Using a GPT-Based VLM: A Preliminary Study on Building a Two-Stage Self-Correction Loop with Structured Output (SLSO) Framework

This study explores a new Self-correction Loop with Structured Output (SLSO) framework to enhance the accuracy of AI-generated findings f...

[2508.02766] The Generative Reasonable Person

The article introduces the 'generative reasonable person,' a tool for assessing how ordinary people judge reasonableness in various legal...

[2509.02594] OpenAIs HealthBench in Action: Evaluating an LLM-Based Medical Assistant on Realistic Clinical Queries

The article evaluates OpenAI's DR. INFO, an LLM-based medical assistant, using the HealthBench benchmark to assess performance on complex...

[2503.15130] A Foundational Theory for Decentralized Sensory Learning

The article presents a foundational theory for decentralized sensory learning, proposing that biological learning mechanisms can be under...

[2503.07599] NeuroChat: A Neuroadaptive AI Chatbot for Customizing Learning Experiences

NeuroChat is a neuroadaptive AI chatbot that personalizes learning experiences by integrating real-time EEG feedback to enhance engagemen...

[2501.12369] DARB-Splatting: Generalizing Splatting with Decaying Anisotropic Radial Basis Functions

This paper introduces DARB-Splatting, a novel approach to 3D reconstruction using Decaying Anisotropic Radial Basis Functions, enhancing ...

[2602.08968] stable-worldmodel-v1: Reproducible World Modeling Research and Evaluation

The paper introduces stable-worldmodel (SWM), a modular ecosystem for world modeling research that enhances reproducibility and standardi...

[2602.02660] MARS: Modular Agent with Reflective Search for Automated AI Research

The paper introduces MARS, a Modular Agent designed for automated AI research, emphasizing cost-aware planning and reflective memory to e...

[2511.07587] Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces

The paper presents a novel framework, Generative Semantic Workspace (GSW), designed to enhance long-context reasoning in Large Language M...

[2511.10853] Advanced Assistance for Traffic Crash Analysis: An AI-Driven Multi-Agent Approach to Pre-Crash Reconstruction

This article presents an AI-driven multi-agent framework for reconstructing traffic crash scenarios, enhancing the accuracy of pre-crash ...

[2510.18631] Comparative Expressivity for Structured Argumentation Frameworks with Uncertain Rules and Premises

This paper explores the expressivity of structured argumentation frameworks that incorporate uncertainty, presenting both theoretical and...

[2510.11661] SR-Scientist: Scientific Equation Discovery With Agentic AI

The paper presents SR-Scientist, a framework that enhances Large Language Models (LLMs) to autonomously discover scientific equations, ou...

[2509.07997] Learning-Based Planning for Improving Science Return of Earth Observation Satellites

The paper presents learning-based approaches to dynamic targeting for Earth observation satellites, demonstrating improved scientific dat...

[2509.03581] Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents

This paper presents a framework for dynamic planning in large language model (LLM) agents, allowing them to efficiently allocate compute ...

[2509.00287] SIGMUS: Semantic Integration for Knowledge Graphs in Multimodal Urban Spaces

The paper presents SIGMUS, a system for semantic integration of multimodal data in urban environments, leveraging large language models t...