https://xitter.cf/t.co/FmX1B3nzjA is working on finding the scaling laws of agents. The first and the best multi-agent framework. Discord: https://xitter.cf/t.co/DRweXf0nOl. Product @Eigent_AI
Joined June 2023
- Tweets1.5K
- Following96
- Followers8.7K
- Likes1.7K
CAMEL-AI.org retweeted
We're releasing AgentVFS, a virtual filesystem interface for AI agents agentvfs.org/
AgentVFS unifies every service into one interface and replaces the need of calling MCP. Stored data becomes one virtual filesystem across services, described by VFS.md, and actions become virtual CLIs, so the agent no longer calls MCP tools at all. AI agents work on live data across every service through the terminal-like interface they know best. They use the Unix tools they learned in training (ls, grep, jq, pipes, loops) and the terminal workflows they practiced in post-training on agentic coding.
We're also releasing VFS-Bench 1.0 agentvfs.org/benchmark/vfs-b…, the first systematic study and benchmark to compare a virtual filesystem with MCP on the same tasks. Compared with MCP, AgentVFS uses up to 88% fewer tokens and has about a 5% higher success rate on average.
CAMEL-AI.org retweeted
What if every SaaS service could be virtualized as files? Excited to release AgentVFS and VFS-Bench 1.0 with @zechengzh: a virtual filesystem interface for AI agents, and the first systematic benchmark comparing it against MCP on the exact same tasks
One task, two interfaces: VFS v.s. MCP. 200 tasks from MCP-Atlas and Toolathlon. Every task runs once through MCP tools and once through AgentVFS, where services show up as files described by VFS.md and actions become CLIs
What we found:
- Claude Opus 5.5: 86% vs 83% pass@1, with 166k vs 617k tokens per task (73% fewer)
- GPT-6.1 Sol: same 75% success, 72% fewer tokens
- GPT-5.6 Luna: 61% → 73% success, 60% fewer tokens
- Up to 88% fewer tokens, and about 5% higher success on average
The part I find most interesting: stronger models gain the most. Opus and Sol save over 70% of their tokens, while smaller models save much less. Frontier models were post-trained heavily on terminal-style coding, and they seem to bring all of it to ls, grep, jq and pipes once you give them that interface
We spend all day building RL environments for agents. One lesson keeps coming back: the interface is part of the environment. The same task can get much easier or much harder depending on how you expose the world to the model
An AgentVFS layer may be how we scale environments for agents. One filesystem in front of every service, and the terminal skills models already have carry over to all of them
We're releasing AgentVFS, a virtual filesystem interface for AI agents agentvfs.org/
AgentVFS unifies every service into one interface and replaces the need of calling MCP. Stored data becomes one virtual filesystem across services, described by VFS.md, and actions become virtual CLIs, so the agent no longer calls MCP tools at all. AI agents work on live data across every service through the terminal-like interface they know best. They use the Unix tools they learned in training (ls, grep, jq, pipes, loops) and the terminal workflows they practiced in post-training on agentic coding.
We're also releasing VFS-Bench 1.0 agentvfs.org/benchmark/vfs-b…, the first systematic study and benchmark to compare a virtual filesystem with MCP on the same tasks. Compared with MCP, AgentVFS uses up to 88% fewer tokens and has about a 5% higher success rate on average.
CAMEL-AI.org retweeted
Eigent v1.0.6 is live! Models, Automations, and Session recovery just got a major upgrade 🚀
What’s new:
🧠 Manage saved models in one place
⏰ Inspect Automation schedules and run history
👋 Choose your Work Profile
🔄 Recover Sessions and handle approvals more reliably
📂 Preserve drafts, terminal history, and finished files
📦 Validate Bundles before sharing and recover failed imports
🔁 Follow clearer upgrade guidance
❤️ Enjoy more control over everyday work
Update to v1.0.6, explore the new features and share your feedback with us 🙌
Read the full release notes: eigent.ai/blog/eigent-v1-0-6…
CAMEL-AI.org retweeted
@Eigent_AI is proud to be part of the SGLang Summit! Come talk to us about RL × Environments × Agents!
Proud to welcome our newest sponsors to SGLang Summit.
In just one week since our public announcement, our sponsor lineup has grown from 11 to 36. Thank you to every sponsor helping bring this community together.
Join 2,000+ engineers, researchers, and builders from across the AI ecosystem for technical sessions, hands-on workshops, and the GPU Expo.
Hear from Lip-Bu Tan, Lilian Weng, Soumith Chintala, Aravind Srinivas, and more. Meet the teams building across AI hardware, infrastructure, models, and applications.
🗓️ November 12–13, 2026
🌉 Fort Mason, San Francisco
🎟️ Get your tickets: sglang.io/summit
CAMEL-AI.org retweeted
Proud to welcome our newest sponsors to SGLang Summit.
In just one week since our public announcement, our sponsor lineup has grown from 11 to 36. Thank you to every sponsor helping bring this community together.
Join 2,000+ engineers, researchers, and builders from across the AI ecosystem for technical sessions, hands-on workshops, and the GPU Expo.
Hear from Lip-Bu Tan, Lilian Weng, Soumith Chintala, Aravind Srinivas, and more. Meet the teams building across AI hardware, infrastructure, models, and applications.
🗓️ November 12–13, 2026
🌉 Fort Mason, San Francisco
🎟️ Get your tickets: sglang.io/summit
CAMEL-AI.org retweeted
Gemini 4 directed a multi-shot 3D Blender scene on Eigent! 🎬
From a calm setup to a delicate wind-blown flight and final landing. 4 connected shots, dynamic DOF, and consistent physics constraints in just one prompt!
Build effortless 3D creations today on Eigent via byok & cloud API!
Today we are rolling out Gemini 4 Argon globally in the Gemini API, to Pro + Ultra in Gemini App, and Ultra subs in Antigravity!
Argon is a huge step forward for Gemini, and a labor of love. This model has been battle tested by over 100,000 people at Google over the last month, with so much new innovation, ambition, and hard work baked into this release. The team has been heads down over the last 6 months working to make this possible across the stack (research, infra, safety, eng, etc).
We rolled the model out to cyber defenders as part of our fairwind program and early access customers over the last 2 weeks, it has been amazing to see and talk to folks who are now using this model daily. Seeing the models writing capability, raw knowledge and persistence for coding, paired with new features like 1M token output when the model needs to work more has gotten me even more excited about our path ahead.
This is just the start of the Gemini 4 era. As you saw with 3.5, 3.6, 3.7, and 3.8 Flash, our iteration speed with Gemini is fast : ) Now with Gemini 4 Argon to work from, I am cannot wait to see the progress continue, and most importantly see what this new model enables for the world.
This is such a special moment in the arc of technology, as millions of people everyday tackle problems they could never have thought possible before. Gemini 4 Argon was built to help you tackle the hardest problems. I have personally felt this spark with Argon and hope you do too. Onwards!!
CAMEL-AI.org retweeted
Gemini 4 Argon is now on Eigent!!
It turns terminal bench author's insights into agent skills in one prompt!
👉 understands RL videos -> extracts key insights with precise timestamps -> produces validated agent skills plus a structured HTML report
Add your Gemini API key on Eigent and try it today!
Today we are rolling out Gemini 4 Argon globally in the Gemini API, to Pro + Ultra in Gemini App, and Ultra subs in Antigravity!
Argon is a huge step forward for Gemini, and a labor of love. This model has been battle tested by over 100,000 people at Google over the last month, with so much new innovation, ambition, and hard work baked into this release. The team has been heads down over the last 6 months working to make this possible across the stack (research, infra, safety, eng, etc).
We rolled the model out to cyber defenders as part of our fairwind program and early access customers over the last 2 weeks, it has been amazing to see and talk to folks who are now using this model daily. Seeing the models writing capability, raw knowledge and persistence for coding, paired with new features like 1M token output when the model needs to work more has gotten me even more excited about our path ahead.
This is just the start of the Gemini 4 era. As you saw with 3.5, 3.6, 3.7, and 3.8 Flash, our iteration speed with Gemini is fast : ) Now with Gemini 4 Argon to work from, I am cannot wait to see the progress continue, and most importantly see what this new model enables for the world.
This is such a special moment in the arc of technology, as millions of people everyday tackle problems they could never have thought possible before. Gemini 4 Argon was built to help you tackle the hardest problems. I have personally felt this spark with Argon and hope you do too. Onwards!!
CAMEL-AI.org retweeted
SETA got accepted to NeurIPS 2026! 🎉
We released the full training scripts for DeepSeek-V4-Flash, GLM-5.2 (LoRA), Inkling-Small, and Qwen3.8-27B, with both GRPO and PPO, alongside 4,500+ open-source, verifiable terminal RL environments
Huge thanks to the @radixark Miles team for helping us scale the experiments!
github.com/camel-ai/seta/tre…
🎉 SETA: Scaling Environments for Terminal Agents has been accepted to the #NeurIPS2026 Evaluations & Datasets Track!
We release SETA-Env, the largest open-source verifiable terminal RL dataset (4,500+ envs), with full synthesis & training pipelines 🧵
arxiv.org/abs/2607.10891
CAMEL-AI.org retweeted
@OpenAI GPT 6 Astra is now on Eigent! ⚡️⚡️⚡️
Our design engineer @douglas_ym used Eigent with GPT 6 Astra to rebuild his old master’s project, TaSH, from just a few photos of the original prototype.
Eigent recreated the full product in Blender, filled in details missing from the original prototype, and automatically rendered a 30-second @Apple style product showcase video.
Download Eigent today. Give Eigent a few images from one of your forgotten projects and see what GPT 6 Astra can rebuild.
Fully open source. Self-hostable on your desktop. Even for confidential projects, your data can stay completely under your control.
CAMEL-AI.org retweeted
Gemini 3.8 now on Eigent! ⚡️⚡️⚡️
We handed it a real finance analyst's job: value Equinix vs Digital Realty, Damodaran-style, straight from SEC filings.
A team of agents researched, checked FX, and built the DCF, then handed back an Excel file you can actually poke at.
Click a number → see the filing it came from. Change an assumption → watch the valuation shift live.
Gemini 3.8 is now supported on Eigent via BYOK and cloud API. Try it today！
CAMEL-AI.org retweeted
Gemini 3.7 Flash now live on Eigent on both byok and cloud api ⚡️
Lightning speed meets unbelievable precision:
> Video-to-3D understanding
> Ultra-detailed, articulated CAD/mesh models (.glb)
> Full PBR materials & emissive lighting
From video reference to production-ready 3D in 3 mins! We also did a comparison with 3.6 Flash it's 2x faster and delivers far richer, more accurate details! 🚀
Download Eigent with free credits to build your own 3D models today!
CAMEL-AI.org retweeted
"behavioral state decay": the failure mode that long-horizon agents forget what matters. meta ai's fix: a memory agent that updates the memory bank and then decides whether to emit a proactive intervention. they train qwen3.5-27b on seta using sft and grpo and show gains on terminal-bench 2.0. great to see seta terminal agent rl envs used this way
- remember when it matters by meta ai @yifannnwu @zhuokaiz: arxiv.org/abs/2607.08716
- our seta project: github.com/camel-ai/seta
CAMEL-AI.org retweeted
we added grok 4.5 to eigent cloud and it is free for new registered users! also check out a quite smooth demo that builds an interactive rocket explorer with eigent x grok 4.5. ofc i know nothing about rocket. probably need someone from @spacexai @SpaceX @elonmusk to verify if the result is good 😆
Grok 4.5 is now live on Eigent Cloud! @spacexai
Download Eigent and get started with 500 free registration credits!
CAMEL-AI.org retweeted
Sharing our ICML’2026 paper Gecko: a stateful simulated environment for agentic tool calling, lead by our intern Zeyu Zhang @zeyu_au at @Eigent_AI x @CamelAIOrg from ANU. It was a great partnership with Prof. @LiangZheng_06 from ANU, @boltzmanns0ul from @AipoLabs. Come to our poster in Seoul to chat more!
Simulated stateful tool calling will become a common technique for training tool calling agents at large scale since the instability of real-world tools. This work shares the same spirit as Toolathlon-GYM we released earlier this year: github.com/eigent-ai/toolath…
If you are interested in scaling tool-use environments or want to partner on training tool-use agents, please dm me!
Will share more progress in training tool-use agents and scaling tool-use environments. Stay tuned!
Execution feedback from real tools can help agents refine tool-use plans. However, repeated real-tool calls may incur costs, hit rate limits, or cause side effects.
Our ICML 2026 paper introduces Gecko, a pre-execution simulation sandbox for tool-use agents.
Given tool schemas or descriptions, Gecko creates simulated tool interfaces, validates tool calls, simulates responses, tracks task state, and returns task-level feedback.
Project: camel-ai.github.io/gecko/
Code: github.com/camel-ai/gecko
Paper: arxiv.org/abs/2602.19218
CAMEL-AI.org retweeted
task state matters. ReAct bases its action on the observation. but the observation is global and does not precisely reflect the consequences of the action. Gecko gives a good task state estimation which better informs actions - all happening in simulation. no pains in real API costs. LLM agnostic.
real gains over state-of-the-art LLMs like GPT5.5 and Gemini-3.0-Pro.
camel-ai.github.io/gecko/
can we make it more efficient? can we generate RL trajectories with it? open questions are there
Execution feedback from real tools can help agents refine tool-use plans. However, repeated real-tool calls may incur costs, hit rate limits, or cause side effects.
Our ICML 2026 paper introduces Gecko, a pre-execution simulation sandbox for tool-use agents.
Given tool schemas or descriptions, Gecko creates simulated tool interfaces, validates tool calls, simulates responses, tracks task state, and returns task-level feedback.
Project: camel-ai.github.io/gecko/
Code: github.com/camel-ai/gecko
Paper: arxiv.org/abs/2602.19218
CAMEL-AI.org retweeted
@Zai_org GLM 5.2 is now live on Eigent from day 0!
threw a real long-horizon task: research 30 companies across 6 sectors of the AI infrastructure stack, structure it into JSON, then build an interactive HTML report. same prompt, 5.1 vs 5.2. where 5.2 pulls ahead:
→ plans deeper and verifies harder.
→ researches wider. Covers 2x the ground.
→ ships a more complete, interactive report.
with a 1M context window, it holds the whole task from research to final deliverable. no dropped threads, no half-finished output.
long tasks are where the difference shows. try it on open source coworker Eigent. 🦾
CAMEL-AI.org retweeted
Will be delivering a talk about CUA-Gym at @CamelAIOrg at 8pm CST/1pm BST, feel free to join!
🚀 Join us for a CAMEL-AI Live Talk with Bowen @BowenWangNLP on CUA-Gym!
CUA-Gym scales verifiable RLVR training data for computer-use agents, with 32,122 tasks across 110 environments. Homepage: cua-gym.xlang.ai
📅 June 5, 2026 | 13:00 London time
Register: forms.gle/x3M1L4tfeSSoX5oH7
CAMEL-AI.org retweeted
Matt @Mattzh1314 is presenting #Articraft at 8am PT / 4pm BST this Friday.
Livestreaming on YouTube: youtube.com/live/yKFWc2sTuAQ
Shoutout to @CamelAIOrg for hosting the event!
Check out Ariticraft 🦾 - a highly efficient agentic system that generates articulated 3D assets fully automatically at scale!
🚀 articraft3d.github.io/