Skip to content
gentic.news — AI News Intelligence Platform
Connecting to the Living Graph…

agent architectures

30 articles about agent architectures in AI news

Seven Voice AI Architectures That Actually Work in Production

An engineer shares seven voice agent architectures that have survived production, detailing their components, latency improvements, and failure modes. This is a practical guide for building real-time, interruptible, and scalable voice AI.

78% relevant

OpenDev Paper Formalizes the Architecture for Next-Generation Terminal AI Coding Agents

A comprehensive 81-page research paper introduces OpenDev, a systematic framework for building terminal-based AI coding agents. The work details specialized model routing, dual-agent architectures, and safety controls that address reliability challenges in autonomous coding systems.

95% relevant

Memory Systems for AI Agents: Architectures, Frameworks, and Challenges

A technical analysis details the multi-layered memory architectures—short-term, episodic, semantic, procedural—required to transform stateless LLMs into persistent, reliable AI agents. It compares frameworks like MemGPT and LangMem that manage context limits and prevent memory drift.

95% relevant

8 RAG Architectures Explained for AI Engineers: From Naive to Agentic Retrieval

A technical thread explains eight distinct RAG architectures with specific use cases, from basic vector similarity to complex agentic systems. This provides a practical framework for engineers choosing the right approach for different retrieval tasks.

85% relevant

AI Agent Types and Communication Architectures: From Simple Systems to Multi-Agent Ecosystems

A guide to designing scalable AI agent systems, detailing agent types, multi-agent patterns, and communication architectures for real-world enterprise production. This represents the shift from reactive chatbots to autonomous, task-executing AI.

72% relevant

Building ReAct Agents from Scratch: A Deep Dive into Agentic Architectures, Memory, and Guardrails

A comprehensive technical guide explains how to construct and secure AI agents using the ReAct (Reasoning + Acting) framework. This matters for retail AI leaders as autonomous agents move from theory to production, enabling complex, multi-step workflows.

76% relevant

Beyond Simple Retrieval: The Rise of Agentic RAG Systems That Think for Themselves

Traditional RAG systems are evolving into 'agentic' architectures where AI agents actively control the retrieval process. A new 5-layer evaluation framework helps developers measure when these intelligent pipelines make better decisions than static systems.

81% relevant

Karpathy's AI Research Agent: 630 Lines of Code That Could Reshape Machine Learning

Andrej Karpathy has released an open-source AI agent that autonomously runs ML research loops—modifying architectures, tuning hyperparameters, and committing improvements to Git while requiring minimal human oversight.

95% relevant

Graph-Based AI Agents Are Revolutionizing Software Development

Researchers are developing graph-based multi-agent systems that dynamically adapt their collaboration patterns to solve complex coding problems more effectively than traditional fixed architectures.

85% relevant

OpenSage: The Dawn of Self-Programming AI Agents That Build Their Own Teams

OpenSage introduces the first agent development kit enabling LLMs to autonomously create AI agents with self-generated architectures, toolkits, and memory systems, potentially revolutionizing how AI systems are designed and deployed.

75% relevant

The Agent Revolution: How AI is Forcing a Fundamental Rewrite of Enterprise Software

Box CEO Aaron Levie predicts a seismic shift from human-operated software to AI agent-driven workflows, requiring API-first architectures and specialized file systems. This transformation will fundamentally change how SaaS companies generate revenue and structure their products.

85% relevant

Subagent AI Architecture: The Key to Reliable, Scalable Retail Technology Development

Subagent AI architectures break complex development tasks into specialized roles, enabling more reliable implementation of retail systems like personalization engines, inventory APIs, and clienteling tools. This approach prevents context collapse in large codebases.

65% relevant

Beyond RAG: How AI Memory Systems Are Creating Truly Adaptive Agents

AI development is shifting from static retrieval systems to dynamic memory architectures that enable continual learning. This evolution from RAG to agent memory represents a fundamental change in how AI systems accumulate and utilize knowledge over time.

85% relevant

74% of Consumers Ready to Delegate Shopping to AI Agents, Study Finds

A study reports 74% of consumers are willing to let an AI agent shop for them. This signals a paradigm shift in retail, with growing trust in autonomous AI for purchasing decisions.

70% relevant

SMAC-Talk: StarCraft Benchmark Tests LLM Agents Against Deceptive Allies

SMAC-Talk extends StarCraft Multi-Agent Challenge with natural language communication, testing LLM agents against deceptive allies. Qwen3.5 models benchmarked; no model exceeds 72% win rate.

70% relevant

Dynamic Workflows: A New Agent Primitive Emerges

Dynamic workflows generate harnesses on the fly for agent orchestrators, enabling branching and verified tasks across coding agents like Claude Code and Codex.

75% relevant

DeepMind paper: hidden web content hijacks agents 86% of the time

DeepMind catalogues 6 attack types where hidden web content hijacks AI agents up to 86% of the time, reframing safety from model alignment to environment trust.

100% relevant

Multi-Agent Systems Hit Diminishing Returns Past 4 Agents

Adding more agents to LLM-driven multi-agent systems degrades performance past a task-dependent optimum, with weaker models peaking at 4 agents and stronger ones at 2.

100% relevant

Agent Harness Scaling: EFC Predicts Success at R2 0.99 vs 0.42

New research introduces Effective Feedback Compute (EFC), which predicts agent success at R2 0.99 vs 0.42 for raw tokens. Reallocating compute by EFC lifts success 3x at the same budget.

88% relevant

Meta-Stanford Survey: Code as Agent Harness Improves AI Reasoning

Meta, Stanford, Illinois survey argues AI agents work better with code as their main working layer, calling it an agent harness.

89% relevant

Microsoft SkillOpt Trains Agent Skills in Text Space, Beats 52/52 Benchmarks

Microsoft's SkillOpt trains agent skills in text space, achieving best or tied-best results in all 52 settings across 6 benchmarks and 7 models.

89% relevant

Neo4j's agent-memory: Open-source unified memory for AI agents via knowledge graphs

Neo4j releases agent-memory, an open-source unified memory layer for AI agents using knowledge graphs, enabling persistent structured recall.

75% relevant

Hybrid A*+RL Agent Beats Pure End-to-End in Unity SR-71 Sim

A hybrid A* + deep RL agent in Unity, trained over 5M PPO steps, switches between classical path planning and learned evasion to navigate an SR-71 through a maze while dodging missiles.

84% relevant

Multi-Agent LLM Systems Fail to Outperform Single Models, Study Finds

New paper finds multi-agent LLM systems underperform single models by 2.3% on reasoning benchmarks, challenging a core assumption in AI engineering.

89% relevant

8-Agent System Builder: Anthropic's Simpler Approach Beat My 2-Day Build

Engineer built 8-agent system in 2 days; Anthropic's simpler 2-agent approach outperformed it. Lesson: minimal agent architecture beats complex orchestration.

81% relevant

Agentick Benchmark: GPT-5 Mini Tops at 0.309, No Agent Paradigm Dominates

Agentick benchmark evaluates RL, LLM, VLM, and hybrid agents on 37 tasks. GPT-5 mini leads at 0.309 ONS, but no paradigm dominates. ASCII beats natural language.

98% relevant

SAEs Predict Agent Tool Failures Before Execution, Paper Shows

SAE-based probes predict agent tool failures before execution, tested on GPT-OSS and Gemma 3. Adds internal observability missing from current external methods.

85% relevant

Microsoft Paper Probes Long-Horizon Agent Generalization Gap

Microsoft Research paper on long-horizon agent generalization identifies failure modes and proposes improvements for extended tasks.

75% relevant

Recursive Multi-Agent Systems Top Hugging Papers; Eywa Bridges LLMs and Scientific Models

Recursive Multi-Agent Systems leads Hugging Papers with 242 upvotes. Eywa and OneManCompany signal a move from chat-based to structural agent collaboration.

89% relevant

Study: AI Agent Groups Fail at Simple Coordination Tasks

A cited study shows AI agent groups fail at simple coordination, challenging multi-agent system assumptions. No paper details disclosed.

85% relevant