MineNPC-Task: Teaching AI to Remember in Minecraft

Kari Jaaskelainen

10 Jan 2026 — 1 min read

How do we know if game-playing AIs can plan, act, and remember like good teammates? Meet MineNPC-Task—a new open benchmark for memory-aware AI agents inside Minecraft’s open world.

Instead of toy prompts, tasks come from real co-play sessions with expert players, then get turned into templates with clear preconditions and dependencies. Machine checks verify progress under a “no out-of-world shortcuts” policy, while the harness logs key events: plan previews, clarifying questions, memory reads/writes, checks, and repairs.

Initial snapshot: GPT-4o tested on 216 subtasks with 8 experienced players.
Common breakdowns: code execution, inventory/tool handling, referencing, and navigation.
Bright spots: mixed-initiative clarifications and lightweight memory often enabled recovery.
Player feedback: positive UX, but stronger long-term memory is needed.

The team is releasing the full suite—tasks, validators, logs, and harness—for transparent, reproducible evaluation of future embodied agents.

Paper: https://arxiv.org/abs/2601.05215v1

Paper: https://arxiv.org/abs/2601.05215v1

Register: https://www.AiFeta.com

AI Minecraft LLM Agents Benchmark Memory HumanAI OpenSource EmbodiedAI

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Why some fine-tuned LLMs miss phishing—and how to fix it

AI that explains itself—by following the science

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A