The Reading Corner

Agentic AI may be reshaping arXiv submissions—here’s the signal

If you’ve felt like arXiv is getting weirdly busy , you’re not imagining it. New research from [Contaldi (2026)](https://arxiv.org/abs/2610.34449) digs...

Oct 27, 2026 0

LLM Engineering Map: Training, Prompts, RAG, and Trust

(An engineer’s plain-language guide based on new research) Introduction If you’ve ever pasted a function, an error message, or a...

Oct 27, 2026 0

Kempe Color-Change Reachability on Claw-Free Graphs

(PSPACE-Complete even for Regular Line Graphs) Introduction If you’ve ever played with “local moves” in puzzles, you already have the...

Oct 26, 2026 0

LLM Autobiographies and the Politics of “Being Seen” Online

Have you ever pasted a prompt like “describe me based on our chats” and felt that weird mix of comfort...

Oct 26, 2026 0

ChatGPT Scores and Novelty Words: Do Abstracts Game Evaluation?

If you’ve ever written (or skimmed) a research abstract, you know the genre: you summarise your work, claim what’s new,...

Oct 25, 2026 0

De-escalation Traps in Medical Chatbots: SIM-UT for Safer Triage

If you’ve ever chatted with a medical assistant bot, you already know the awkward truth: real people don’t talk like...

Oct 25, 2026 0

Governance-First AI GPT for EU AI Act SME Compliance (TESSA)

If you’re an SME trying to make sense of the EU AI Act , you don’t need more generic “AI...

Oct 24, 2026 0

Memory-Aware Rewarding: Train LLMs to Use Your ChatGPT Memories

=============================================================== Introduction If you’ve ever used a chat assistant that “remembers” things about you, you probably had the same thought:...

Oct 24, 2026 0

Tool Selection in Tool-Heavy Agents: Train Tiny LLMs to Pick the Right API

If you’ve ever built an AI “agent” that can use external tools (APIs, web search, booking systems, internal dashboards), you’ve...

Oct 23, 2026 0

Submit Content