WayToClawEarn
Medium impactCursor Blog

Cursor releases Composer 2.5: Innovation in training methods makes AI coding agents smarter

Cursor released Composer 2.5 on May 18, 2026, based on Kimi K2.5 checkpoint training, introducing directed text feedback reinforcement learning and sharding Muon optimizer. The new model has significantly improved long-term task execution, instruction following and collaborative experience, and is priced at $0.50/M input token. This article breaks down the technical details and practical suggestions.

WayToClawEarn EditorialPublished May 19, 2026Updated Aug 8, 2026

Editorial review of public sources · AI-assisted drafting. How we work · Original source

Core conclusion

On May 18, 2026, Cursor officially released Composer 2.5—a major upgrade to its AI coding agent model. The new version is based on the Moonshot Kimi K2.5 open source checkpoint, using directional text feedback reinforcement learning and sharded Muon optimizer training, which has significantly improved the continuous execution of long tasks, complex instruction following, and collaborative experience. Pricing $0.50/M input token, $2.50/M output token, usage doubled in the first week.

Key Points

  • Release time: 2026-05-18 -Affected objects: AI coding agent users, Cursor users, automated pipeline developers
  • Core changes: directed feedback RL + sharding Muon optimizer, both intelligence and usability improvements

Background and trigger events

The Cursor team officially disclosed the technical details of Composer 2.5 on the official blog. The new model is positioned as "smarter, more suitable for long-term tasks, and more enjoyable to collaborate with" - this is not only an upgrade in model capabilities, but also an evolution in the form of AI coding agent products. Composer 2.5, like its predecessor Composer 2, is based on Moonshot's Kimi K2.5 open source checkpoint fine-tuning training, but Cursor is teaming up with SpaceXAI to train a significantly larger model from scratch with 10 times the computing power.

This release also reflects a larger trend: AI coding tools no longer compete with "who can write a line of code correctly", but with "who can run the entire project." Credit allocation, behavior calibration, and reward hacker protection in long-context rollout—these issues that were originally only discussed in RL research have now become the core competitiveness of the product.

Key Impact (by Dimension)

The following table summarizes the changes and practical significance of each dimension of Composer 2.5:

DimensionsChangeWhat it means to usRecommended actions
IntelligenceDirected text feedback RL is added to training, and credit allocation in long Rollout is more accurateAI coding tools can handle more complex multi-step tasks, with fewer errors from beginning to endUse Cursor as one of the preferred tools for AI coding to test long process tasks
BehaviorCommunication style and effort calibration are optimized by RL, and the collaboration experience is improvedInteraction is no longer rigid, AI can judge when to take the initiative and when to waitUpdate Composer to the latest version to experience the optimized collaboration mode
ArchitectureSharded Muon + dual grid HSDP, MoE training efficiency is highermeans faster iteration speed and lower inference costPay attention to the subsequent release window of larger models, and the computing cost performance will continue to improve
Pricing$0.50/M input, $2.50/M outputFor high-frequency coding users, Composer 2.5 is more cost-effective than similar modelsTry double the usage this week to evaluate whether it is worth subscribing
Training10x computing power to train larger models from scratch (in cooperation with SpaceXAI)The next generation model is expected to make a qualitative leapPay attention to subsequent announcements, the current Composer 2.5 is the best version available

Adaptation suggestions

If you are a Cursor user, here are a few actions you can get started with:

  • Upgrade to latest version of Cursor: Enabled by default in Composer 2.5. New users can experience it after creating a project.
  • Test long task execution: Find a coding job that you previously needed to do manually in multiple steps, and give it to Composer 2.5 in one go. The new version's improved credit distribution in long rollouts means it can better track what it's doing.
  • Try complex instructions: Composer 2.5 training adds directed text feedback - you can give more vague instructions that require reasoning and watch it correct itself through "prompts" in the context.
  • Take full advantage of double the dosage in the first week: Composer 2.5 doubles the dosage in the first 7 days, suitable for high-intensity testing.

Task List (Example)

  • Upgrade Cursor to the latest version
  • Select a pending complex coding task as a test case
  • Note the behavioral changes in Composer 2.5: Is the communication style more natural?
  • Record the completion rate of long Rollout (>1000 steps), compared with Composer 2

Example: Quickly verify upgrade

How to confirm Composer 2.5 is enabled:

terminal

# Cursor (Cmd+Shift+P)

# Composer: Show Version

# 2.5
#
cursor --version

Muon

Composer 2.5 RL

(Targeted RL with Textual Feedback) RL Rollout 。 Rollout token——AI 100 , 900 。 RL ""。

Composer 2.5 ,,「...」。,。""。

** Muon + HSDP** MoE(),Muon GPU -。Cursor ——。 expert/non-expert HSDP ,CP=2 EP=8 8 GPU ( 16 )。

Composer 2.5

()

CursorOpenAI(GPT )、Claude(Claude Code)、DeepSeek. These tools are core components of AI coding and automation workflows.

Internal link guidance

View source →

Disclaimer: this site shares educational insights only, for inspiration and reference. No outcome guarantee; external execution and decisions are your own responsibility.