LongNAP: New Reasoning Model Predicts User Actions Over Long Contexts
CCgong · x · 2026-08-04
To move beyond assistants that require constant step-by-step instructions, researchers introduced LongNAP, a reasoning model designed to predict user actions over long contexts.
- Core Capability: Anticipates what the user will do next across extended interactions.
- Training Data: Trained on 1,800 hours of computer use from 20 different users.
- Goal: Shifts AI assistants from passive responders to proactive collaborators.
More from coding & agent
- Stop Burning Money on Opus: The DeepSeek V4 Flash Fix — PrajwalTomar_ · 2026-08-04
- Ditching Claude Code: Migrating Complex Workflows to Open-Weight Models — TheZachMueller · 2026-08-04
- Reducing LLM API Costs: How Semantic Cache Handles Repetitive Queries — qdrant_engine · 2026-08-04
- Opinion: Bash Is All AI Agents Need for Tool Use — NielsRogge · 2026-08-04
- From Representation Learning to Continual Learning Agents: New AIxIA Paper — v_lomonaco · 2026-08-04
- Managing Long Contexts: Devs Share Workarounds for LLM 'Lost in the Middle' — Entire-Ship8618 · 2026-08-04