🤖 LLM, Agent - inarcissuss

Discussed on Substack

🧠Claude alexweil.github.io·

How good a detective is an AI? A Sherlock Holmes board game as an LLM-agent eval

Discussed on Hacker News

🧠LLM Reasoning arXiv·

How Do Tool-Augmented LLM Agents Perform on Real-World Energy Analytics Tasks?

🔧Tool Use medium.com

Four agentic frameworks, one real problem.

🔧Tool Use IAB Tech Lab·

Seeing the Forest for the Trees: Using Open Industry standards as foundations for Agentic AI

🤖Agentic Engineering Dries Buytaert·

Drupal's role in agentic workflows

Covers 3 stories including Do you respect 'Vibe Coders'? Can you actually call them devs?

💡AI Reasoning itnext.io·

Inside MAI-Thinking-1: How Microsoft Built a Reasoning Model From Scratch

🤖LLM Agents Nature·

Inducing state anxiety in LLM agents reproduces human-like biases in consumer decision-making

🤖Agentic Engineering PPC Land·

LiveRamp pilots agentic AI to fix commerce media's workflow gap

🤖AI Assistants GitHub·

ExoModel – the object calls the LLM; you just describe what you want

Discussed on Hacker News

🛡️AI Security arXiv·

Securing LLM-Agent Long-Term Memory Against Poisoning: Non-Malleable, Origin-Bound Authority with Machine-Checked Guarantees

🤖Agentic Engineering MicroScope

Roundtable: UK tech chiefs on agentic AI, workforce culture and tokenomics

🤖AI Towards AI·

Build a Hybrid RAG System with FAISS, BM25, LangGraph and Claude Sonnet Model

🏗️Agent Infrastructure GitHub·

I built a mini agent-tool framework to actually understand how LangGraph/CrewAI register tools

Discussed on DEV

🧠LLM Reasoning arXiv·

Quantization Inflates Reasoning: Token Inflation as a Hidden Cost of Low-Bit Reasoning Models

🎼LLM Orchestration arXiv·

DeepBD: A Grounded Agentic Workflow for Variant Prioritization and Diagnosis of Genetic Birth Defects

🤖AI Development arXiv·

langchain-ai/langchain langchain-openai==1.3.3

Stop Using LangChain for AI Agents. Here’s Why.

My LLM Agent Ran for Six Hours. It Did Nothing Useful. That Was My Fault.

Agentic RL: Frameworks and Best Practices

How good a detective is an AI? A Sherlock Holmes board game as an LLM-agent eval

How Do Tool-Augmented LLM Agents Perform on Real-World Energy Analytics Tasks?

Four agentic frameworks, one real problem.

Seeing the Forest for the Trees: Using Open Industry standards as foundations for Agentic AI

Drupal's role in agentic workflows

Inside MAI-Thinking-1: How Microsoft Built a Reasoning Model From Scratch

Inducing state anxiety in LLM agents reproduces human-like biases in consumer decision-making

LiveRamp pilots agentic AI to fix commerce media's workflow gap

ExoModel – the object calls the LLM; you just describe what you want

Securing LLM-Agent Long-Term Memory Against Poisoning: Non-Malleable, Origin-Bound Authority with Machine-Checked Guarantees

Roundtable: UK tech chiefs on agentic AI, workforce culture and tokenomics

Build a Hybrid RAG System with FAISS, BM25, LangGraph and Claude Sonnet Model

I built a mini agent-tool framework to actually understand how LangGraph/CrewAI register tools

Quantization Inflates Reasoning: Token Inflation as a Hidden Cost of Low-Bit Reasoning Models

DeepBD: A Grounded Agentic Workflow for Variant Prioritization and Diagnosis of Genetic Birth Defects

The Hitchhiker's Guide to Agentic AI: From Foundations to Systems