Microsoft releases Fara-7B, a multimodal intelligent agent with 7 billion parameters, designed specifically for computer usage scenarios. It can process screenshots and text simultaneously, directly predicting parameterized thought chains and operational actions, built on Qwen 2.5-VL, with a 128k context window, trained on 64 H100 chips for 2.5 days, and released under MIT license. It perceives browser input through screenshots, combining reasoning and historical state prediction to determine the next actions and parameters such as coordinates, relying on large-scale fully synthetic data. It has the ability to plan and execute advanced tasks, and employs robust post-training safety alignment, capable of refusing inappropriate tasks and pausing at critical points. It can be deployed and interacted with via GitHub, vllm, and fara-cli, for automating web tasks.

MeNews

2026-05-26 16:53:07

Abstract generation in progress

AIMPACT News, May 16 (UTC+8), Microsoft released Fara-7B, its first small language model with 7 billion parameters specifically designed for computer usage scenarios. The model adopts a multimodal decoder architecture, capable of receiving screenshot images and text context, directly predicting parameterized thought chains and operational actions. Built on Qwen 2.5-VL (7B), supporting a 128k context length, trained over 2.5 days on 64 H100 GPUs, and released under the MIT license on November 24, 2025. Fara-7B perceives browser input through screenshots, combining internal reasoning and historical state records to predict the next action and parameters (such as click coordinates). Training relies on large-scale fully synthetic datasets. The model can plan and execute advanced tasks such as booking restaurants, applying for jobs, and planning trips. For safety alignment, it employs robust fine-tuning methods, has key point recognition capabilities, can refuse seven categories of policy-violating tasks, and pauses operations at critical stopping points like inputting personal information or completing purchases. Users can deploy and interact via GitHub repositories, vllm, and fara-cli tools, mainly applied to automated web tasks. (Source: InFoQ)

View Original

This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.

8 Likes

Reward
8
8
3
Share

Comment

Add a comment

AirdropNightwatch

· 5h ago

When it comes to browser automation, it feels like it's going head-to-head with Browser-use and Computer-use.

View OriginalReply0

MintCondition

· 6h ago

Web page task automation, finally no need to write a bunch of selectors.

View OriginalReply0

SaveABitOnGasFees

· 6h ago

What proportion of data was used for post-training alignment? The paper will be released soon.

View OriginalReply0

GateUser-83c80dd0

· 6h ago

7B parameters for agent planning, lightweight but capability boundaries need to be empirically tested

View OriginalReply0

GateUser-bee672a5

· 6h ago

fara-cli deployment experience pending testing, hope it doesn't turn out like some projects with poor documentation

View OriginalReply0

Half-SectionSucculent

· 6h ago

Coordinate prediction + step-by-step reasoning, fine-grained control is far better than a pure text API

View OriginalReply0

0xLateCoffee

· 6h ago

128k context + screenshot awareness, this combination is quite powerful

View OriginalReply0

CandleChaser

· 6h ago

MIT License praised, 7B can run locally now

View OriginalReply0

Trending Topics
View More
#
StockTradingChallengeUpTo17000U
16.22M Popularity
#
USStrikesIran
9.32M Popularity
#
GatePredictionMarketAddsSmartMoneyTracking
13.8M Popularity
#
InstitutionalCapitalRotatesFromBTCToHYPEAndXRP
14.33M Popularity
#
TradeCFDWinGold
3.08M Popularity

Pinned

Sitemap

Microsoft releases the first 7B-parameter computer-controlled intelligent agent model Fara-7B

Trending Topics

StockTradingChallengeUpTo17000U

USStrikesIran

GatePredictionMarketAddsSmartMoneyTracking

InstitutionalCapitalRotatesFromBTCToHYPEAndXRP

TradeCFDWinGold

Pinned