Holo3.1: Fast & Local Computer Use Agents
• 36
AI & ML interests
None defined yet.
Articles
sergiopaniego
posted an update 6 days ago
Post
593
Something I really like when I study a subject is understanding its history, how it reached the point where it is today
I did that exercise for RL in post-training: from RLHF and PPO, to verifiable rewards, to the GRPO family of variants, to agents acting in environments. Everything is backed by what the labs themselves say in their public reports (DeepSeek, Qwen, Kimi, GLM-5, Nemotron, Mistral and more), in their own words
This is the companion piece to Class 3 of our Training Agents series with @burtenshaw . The class explains how GRPO works, with three hands-on experiments. The article shows where the same ideas appear at frontier scale
https://huggingface.co/blog/sergiopaniego/agentic-rl-2026
I did that exercise for RL in post-training: from RLHF and PPO, to verifiable rewards, to the GRPO family of variants, to agents acting in environments. Everything is backed by what the labs themselves say in their public reports (DeepSeek, Qwen, Kimi, GLM-5, Nemotron, Mistral and more), in their own words
This is the companion piece to Class 3 of our Training Agents series with @burtenshaw . The class explains how GRPO works, with three hands-on experiments. The article shows where the same ideas appear at frontier scale
https://huggingface.co/blog/sergiopaniego/agentic-rl-2026
sergiopaniego
posted an update 11 days ago
Post
238
we just released a new blog "Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv"
you can take a real coding agent (OpenCode), let it run its own tool loop against real coding problems, and train it with RL on the exact tokens it produced
and every rollout runs in its own remote HF sandbox, so rollouts scale out beyond one machine
the loop:
- OpenCode owns its tool loop inside an OpenEnv sandbox
- an in-sandbox proxy records the real token ids + logprobs, per turn
- a hidden-test verifier scores the result, and that is the reward
- TRL trains with AsyncGRPO, weights sync back to vLLM over NCCL
blog + runnable example: https://huggingface.co/blog/sergiopaniego/trl-openenv-harness-training
you can take a real coding agent (OpenCode), let it run its own tool loop against real coding problems, and train it with RL on the exact tokens it produced
and every rollout runs in its own remote HF sandbox, so rollouts scale out beyond one machine
the loop:
- OpenCode owns its tool loop inside an OpenEnv sandbox
- an in-sandbox proxy records the real token ids + logprobs, per turn
- a hidden-test verifier scores the result, and that is the reward
- TRL trains with AsyncGRPO, weights sync back to vLLM over NCCL
blog + runnable example: https://huggingface.co/blog/sergiopaniego/trl-openenv-harness-training
- 3 replies
sergiopaniego
posted an update 12 days ago
Post
2578
LFM2.5-2.6B just dropped!
and the @liquidai blog comes with some nice details about the training procedure, so let's analyze it.
basically, a full agent training pipeline but compressed into 2.6B
base model → SFT → specialized teachers per domain (SFT + RLVR) → on-policy distillation back into one student → agentic RL
the two most interesting stages
→ MOPD: the student generates, each prompt routes to its domain teacher for token-level feedback. teachers branch from the same SFT checkpoint, so their signal stays close to the student's distribution
→ agentic RL: multi-turn GRPO inside real harnesses (OpenClaw, Hermes Agent), one sandbox per rollout, a proxy captures token-level trajectories while the harness stays a black box
this makes a 2.6B that beats much larger models on instruction following and tool use
SFT, distillation, RL, RL envs: exactly what we're covering in our Training Agents livestream series (next one coming soon!)
→ model: LiquidAI/LFM2.5-2.6B
→ blog: https://www.liquid.ai/blog/lfm2-5-2-6b
→ live series: https://www.youtube.com/playlist?list=PLo2EIpI_JMQvQZm-kVlz4wY1vWF0LBcf5
and the @liquidai blog comes with some nice details about the training procedure, so let's analyze it.
basically, a full agent training pipeline but compressed into 2.6B
base model → SFT → specialized teachers per domain (SFT + RLVR) → on-policy distillation back into one student → agentic RL
the two most interesting stages
→ MOPD: the student generates, each prompt routes to its domain teacher for token-level feedback. teachers branch from the same SFT checkpoint, so their signal stays close to the student's distribution
→ agentic RL: multi-turn GRPO inside real harnesses (OpenClaw, Hermes Agent), one sandbox per rollout, a proxy captures token-level trajectories while the harness stays a black box
this makes a 2.6B that beats much larger models on instruction following and tool use
SFT, distillation, RL, RL envs: exactly what we're covering in our Training Agents livestream series (next one coming soon!)
→ model: LiquidAI/LFM2.5-2.6B
→ blog: https://www.liquid.ai/blog/lfm2-5-2-6b
→ live series: https://www.youtube.com/playlist?list=PLo2EIpI_JMQvQZm-kVlz4wY1vWF0LBcf5
- 3 replies
sergiopaniego
posted an update 17 days ago
Post
2623
Simon Willison (@simonw ) has asked every new model to draw a pelican riding a bicycle for some time now
you look at the drawing and you know. but there is no number, so nothing can train against it, no?
I turned this idea into an rl env in OpenEnv. now, you can eval any model against it, and train against it with TRL
read the details!🤓
https://huggingface.co/blog/sergiopaniego/pelican-env-openenv
you look at the drawing and you know. but there is no number, so nothing can train against it, no?
I turned this idea into an rl env in OpenEnv. now, you can eval any model against it, and train against it with TRL
read the details!🤓
https://huggingface.co/blog/sergiopaniego/pelican-env-openenv
- 2 replies
sergiopaniego
posted an update 18 days ago
Post
203
yesterday we had Class 3 of the Training Agents live series
we went through how GRPO works in depth and applied it to real experiments with TRL
sharing the resources in case you want to dig in, enjoy!
🎥 session recording: https://www.youtube.com/watch?v=ztdTed5egrM
📄 slides with links: https://docs.google.com/presentation/d/19v5_HR5B-1CPHuoZ-RXjhgBrGFXGnBNd6TfLhsXWT1c/edit?usp=sharing
we went through how GRPO works in depth and applied it to real experiments with TRL
sharing the resources in case you want to dig in, enjoy!
🎥 session recording: https://www.youtube.com/watch?v=ztdTed5egrM
📄 slides with links: https://docs.google.com/presentation/d/19v5_HR5B-1CPHuoZ-RXjhgBrGFXGnBNd6TfLhsXWT1c/edit?usp=sharing
sergiopaniego
posted an update 20 days ago
Post
2900
quick reminder! 🚨
tomorrow (Tuesday, July 28), we're back with Class 3 of the Training Agents live series
🧠 what: reinforcement learning for training agents (GRPO): how it works, how to implement it in TRL, and end-to-end examples
🗓️ when: Tuesday, July 28 - 🕔 5:00 PM CEST / 8:30 PM IST
📍 where: Live on @huggingface 's X, YouTube, and LinkedIn
live: https://www.youtube.com/watch?v=ztdTed5egrM
class 1: https://x.com/SergioPaniego/status/2069382207618379813
class 2: https://x.com/SergioPaniego/status/2075180665184686187
tomorrow (Tuesday, July 28), we're back with Class 3 of the Training Agents live series
🧠 what: reinforcement learning for training agents (GRPO): how it works, how to implement it in TRL, and end-to-end examples
🗓️ when: Tuesday, July 28 - 🕔 5:00 PM CEST / 8:30 PM IST
📍 where: Live on @huggingface 's X, YouTube, and LinkedIn
live: https://www.youtube.com/watch?v=ztdTed5egrM
class 1: https://x.com/SergioPaniego/status/2069382207618379813
class 2: https://x.com/SergioPaniego/status/2075180665184686187
- 1 reply
sergiopaniego
posted an update 23 days ago
Post
223
you can now train your own coding agents with trl + openenv, starting with opencode
we just added end-to-end support for training agent harnesses:
> TRL: a loop-owning training path (AsyncGRPOTrainer + HarnessRolloutWorker) that launches the agent in an OpenEnv session, reads back its trace, reconstructs the training samples, and trains with AsyncGRPO
> OpenEnv: the OpenCode harness environment plus a transparent proxy that forwards the agent's model calls and records each turn's token ids and logprobs
you train the actual opencode agent as is, it runs its own loop and tools and the policy learns from the exact tokens it produced
we're shipping a self-contained example: local subprocess sandbox, DeepCoder problems, validated on Qwen3-8B.
> example: https://github.com/huggingface/trl/blob/main/examples/scripts/openenv/opencode.py
> docs: https://huggingface.co/docs/trl/main/openenv
and we're working actively on both sides so expect more 🤓
we just added end-to-end support for training agent harnesses:
> TRL: a loop-owning training path (AsyncGRPOTrainer + HarnessRolloutWorker) that launches the agent in an OpenEnv session, reads back its trace, reconstructs the training samples, and trains with AsyncGRPO
> OpenEnv: the OpenCode harness environment plus a transparent proxy that forwards the agent's model calls and records each turn's token ids and logprobs
you train the actual opencode agent as is, it runs its own loop and tools and the policy learns from the exact tokens it produced
we're shipping a self-contained example: local subprocess sandbox, DeepCoder problems, validated on Qwen3-8B.
> example: https://github.com/huggingface/trl/blob/main/examples/scripts/openenv/opencode.py
> docs: https://huggingface.co/docs/trl/main/openenv
and we're working actively on both sides so expect more 🤓
- 1 reply
sergiopaniego
posted an update 24 days ago
Post
1530
you can train DiffusionGemma (a block-diffusion LLM) in TRL! and we're sharing an example for it
TRL trainers are made to be easily extended and adapted to different real-world use cases.
in this one, with a single method overridden in SFTTrainer (compute_loss), you can train this model
> example: https://github.com/huggingface/trl/blob/main/examples/scripts/sft_diffusion_gemma.py
TRL trainers are made to be easily extended and adapted to different real-world use cases.
in this one, with a single method overridden in SFTTrainer (compute_loss), you can train this model
> example: https://github.com/huggingface/trl/blob/main/examples/scripts/sft_diffusion_gemma.py
sergiopaniego
posted an update 25 days ago
Post
249
join us next Tuesday, July 28, for Class 3 of the Training Agents live series!
we'll dive into reinforcement learning for agent training, covering the intuition behind GRPO, how it works, and how to implement it in TRL with practical, e2e examples
see you there 🤠
live: https://www.youtube.com/live/ztdTed5egrM
> in case you missed class 1:
https://x.com/SergioPaniego/status/2069382207618379813
> and in case you missed class 2: https://x.com/SergioPaniego/status/2075180665184686187
we'll dive into reinforcement learning for agent training, covering the intuition behind GRPO, how it works, and how to implement it in TRL with practical, e2e examples
see you there 🤠
live: https://www.youtube.com/live/ztdTed5egrM
> in case you missed class 1:
https://x.com/SergioPaniego/status/2069382207618379813
> and in case you missed class 2: https://x.com/SergioPaniego/status/2075180665184686187
sergiopaniego
posted an update about 1 month ago
Post
7756
Frontier models use distillation as a step of their post-training pipelines.
In 2026 it has three jobs: compress a big model into a small one, merge RL experts into a single model, and let a model teach itself.
I wrote up which frontier models use each one and how: https://huggingface.co/blog/sergiopaniego/distillation-2026
It pairs with Class 2 of the Training an Agent series Ben and I are doing, where we teach these techniques hands-on with TRL!
In 2026 it has three jobs: compress a big model into a small one, merge RL experts into a single model, and let a model teach itself.
I wrote up which frontier models use each one and how: https://huggingface.co/blog/sergiopaniego/distillation-2026
It pairs with Class 2 of the Training an Agent series Ben and I are doing, where we teach these techniques hands-on with TRL!
- 3 replies
Post
106
Hello people of Huggingface,
Our model Holo3 is #1 on OSWorld-verified — and it's now powering a fully managed computer use agent API in open beta.
Web browser is live. Pass a task → isolated cloud session → structured output. Python + TS SDKs. Works anywhere, even with no API on the target site. Desktop environment coming soon.
Come join the open beta, we're excited to see what you'll build!
Beta → bit.ly/HCompanyPlatform
Docs → hub.hcompany.ai/computer-use-agents
Model → huggingface.co/Hcompany/holo31
Discord → bit.ly/HCompanyDiscord
Our model Holo3 is #1 on OSWorld-verified — and it's now powering a fully managed computer use agent API in open beta.
Web browser is live. Pass a task → isolated cloud session → structured output. Python + TS SDKs. Works anywhere, even with no API on the target site. Desktop environment coming soon.
Come join the open beta, we're excited to see what you'll build!
Beta → bit.ly/HCompanyPlatform
Docs → hub.hcompany.ai/computer-use-agents
Model → huggingface.co/Hcompany/holo31
Discord → bit.ly/HCompanyDiscord
- 3 replies
sergiopaniego
posted an update about 2 months ago
Post
384
TRL v1.7.0 is out‼️
+ continuous batching makes GRPO and RLOO 1.25x faster at -16 GB
+ proper MoE post-training across GRPO/RLOO/AsyncGRPO
+ new GMPO trainer
+ AsyncGRPO weight sync + padding-free
+ more
https://github.com/huggingface/trl/releases/tag/v1.7.0
wrote a small article about the continuous batching for GRPO feature
https://huggingface.co/blog/sergiopaniego/cb-trl-grpo
+ continuous batching makes GRPO and RLOO 1.25x faster at -16 GB
+ proper MoE post-training across GRPO/RLOO/AsyncGRPO
+ new GMPO trainer
+ AsyncGRPO weight sync + padding-free
+ more
https://github.com/huggingface/trl/releases/tag/v1.7.0
wrote a small article about the continuous batching for GRPO feature
https://huggingface.co/blog/sergiopaniego/cb-trl-grpo
sergiopaniego
posted an update about 2 months ago
Post
371
Continuous batching just landed in TRL for GRPO!
At 64 generations it runs faster and uses less VRAM than plain generate, no vLLM needed
How it works and when to reach for it, below
https://huggingface.co/blog/sergiopaniego/cb-trl-grpo
At 64 generations it runs faster and uses less VRAM than plain generate, no vLLM needed
How it works and when to reach for it, below
https://huggingface.co/blog/sergiopaniego/cb-trl-grpo
sergiopaniego
posted an update 2 months ago
Post
350
GLM-5.2 is open and comes with competitive performance against opus 4.8
day-0 in transformers + vllm + sglang, mit license 🤗
on the post-training side: critic-based ppo for variable-length agentic rollouts (ppo is back!) + an online anti-reward-hacking module that feeds the agent dummy info when it tries to cheat
day-0 in transformers + vllm + sglang, mit license 🤗
on the post-training side: critic-based ppo for variable-length agentic rollouts (ppo is back!) + an online anti-reward-hacking module that feeds the agent dummy info when it tries to cheat
sergiopaniego
posted an update 2 months ago
Post
3983
OpenEnv has a new home: github.com/huggingface/OpenEnv
Starting today, it's coordinated by a committee that includes Meta-PyTorch, Reflection, Unsloth, Modal, Prime Intellect, Nvidia, Mercor, Fleet AI, and Hugging Face
frontier labs train their models and their harnesses together. Claude knows Claude Code. GPT-5.5 knows Codex. that's not an accident, it's training. open-source models deserve the same magic, but pulling that off requires infrastructure that belongs to everyone, not one lab
OpenEnv is that layer. one api, any harness, any trainer, any environment
Rewards and training loops stay in TRL, Unsloth, wherever you already work. OpenEnv is the socket they all plug into
Get involved!
Full announcement: https://huggingface.co/blog/openenv-agentic-rl
Starting today, it's coordinated by a committee that includes Meta-PyTorch, Reflection, Unsloth, Modal, Prime Intellect, Nvidia, Mercor, Fleet AI, and Hugging Face
frontier labs train their models and their harnesses together. Claude knows Claude Code. GPT-5.5 knows Codex. that's not an accident, it's training. open-source models deserve the same magic, but pulling that off requires infrastructure that belongs to everyone, not one lab
OpenEnv is that layer. one api, any harness, any trainer, any environment
Rewards and training loops stay in TRL, Unsloth, wherever you already work. OpenEnv is the socket they all plug into
Get involved!
Full announcement: https://huggingface.co/blog/openenv-agentic-rl
sergiopaniego
posted an update 2 months ago
Post
368
Frontier agents are this good partly because the model was trained inside the very harness it ships with.
NVIDIA's new paper "Polar: Agentic RL on Any Harness at Scale" brings that recipe to the open: it turns coding harnesses like Codex, Claude Code, Qwen Code or Pi into RL training environments without touching their internals.
The core idea: every agent, however complex or closed, talks to a model through an API, so they put a proxy there. The harness runs exactly like in production while the proxy records prompts, sampled token ids and logprobs. Trajectories get rebuilt outside, token faithful, so gradients hit the exact tokens the policy sampled.
The gains are consistent across all four harnesses. Same Qwen3.5-4B, plain GRPO, evaluated on SWE-Bench Verified:
Codex 3.8 → 26.4 (+22.6)
Claude Code 29.8 → 34.6 (+4.8)
Qwen Code 34.6 → 35.2 (+0.6)
Pi 34.2 → 40.4 (+6.2)
The biggest gains appear on unfamiliar execution paths, Codex being the clearest case. The takeaway: you are not just training a model, you are training the model + harness system.
Two engineering pieces make it work at scale. Async worker pools isolate container boots (CPU), agent execution (GPU) and long tail test runs, so slow runtimes never block the GPUs. And prefix merging stitches hundreds of captured API calls back into contiguous traces: 5.4x faster trainer updates and rollout GPUs at 88% utilization.
It also doubles as an SFT data factory: 504 test verified agent traces from a 122B teacher, multi-turn conversations averaging 104 messages each, coming to the Hub under Apache 2.0 (release pending review).
Paper authors: Binfeng Xu, Hao Zhang, Shaokun Zhang, Songyang Han, Mingjie Liu, Jian Hu, Shizhe Diao, Zhenghui Jin, Yunheng Zou, Michael Demoret, Jan Kautz and Yi Dong.
> Paper: Polar: Agentic RL on Any Harness at Scale (2605.24220)
> Code: https://github.com/NVIDIA-NeMo/ProRL-Agent-Server
> Training data: NovaSky-AI/SkyRL-v0-293-data
NVIDIA's new paper "Polar: Agentic RL on Any Harness at Scale" brings that recipe to the open: it turns coding harnesses like Codex, Claude Code, Qwen Code or Pi into RL training environments without touching their internals.
The core idea: every agent, however complex or closed, talks to a model through an API, so they put a proxy there. The harness runs exactly like in production while the proxy records prompts, sampled token ids and logprobs. Trajectories get rebuilt outside, token faithful, so gradients hit the exact tokens the policy sampled.
The gains are consistent across all four harnesses. Same Qwen3.5-4B, plain GRPO, evaluated on SWE-Bench Verified:
Codex 3.8 → 26.4 (+22.6)
Claude Code 29.8 → 34.6 (+4.8)
Qwen Code 34.6 → 35.2 (+0.6)
Pi 34.2 → 40.4 (+6.2)
The biggest gains appear on unfamiliar execution paths, Codex being the clearest case. The takeaway: you are not just training a model, you are training the model + harness system.
Two engineering pieces make it work at scale. Async worker pools isolate container boots (CPU), agent execution (GPU) and long tail test runs, so slow runtimes never block the GPUs. And prefix merging stitches hundreds of captured API calls back into contiguous traces: 5.4x faster trainer updates and rollout GPUs at 88% utilization.
It also doubles as an SFT data factory: 504 test verified agent traces from a 122B teacher, multi-turn conversations averaging 104 messages each, coming to the Hub under Apache 2.0 (release pending review).
Paper authors: Binfeng Xu, Hao Zhang, Shaokun Zhang, Songyang Han, Mingjie Liu, Jian Hu, Shizhe Diao, Zhenghui Jin, Yunheng Zou, Michael Demoret, Jan Kautz and Yi Dong.
> Paper: Polar: Agentic RL on Any Harness at Scale (2605.24220)
> Code: https://github.com/NVIDIA-NeMo/ProRL-Agent-Server
> Training data: NovaSky-AI/SkyRL-v0-293-data
sergiopaniego
posted an update 2 months ago
Post
318
The recording from our talk: "From Responses To Trajectories: Multi-Turn and Multi-Environment RL" from PyTorch Conf Europe is live!
@kashif and I covered the latest advances in multi-turn GRPO in TRL: trajectories, tool use, envs, and agentic post-training at scale
https://www.youtube.com/watch?v=rPBeXFntJSU
@kashif and I covered the latest advances in multi-turn GRPO in TRL: trajectories, tool use, envs, and agentic post-training at scale
https://www.youtube.com/watch?v=rPBeXFntJSU
sergiopaniego
posted an update 2 months ago
Post
251
how do you sync a trillion parameter model every RL step without a shared cluster? we just wrote a blog about it, led by @aminediroHF
what I like the most is the way it proves you can use the Hub for basically everything 🧐 → trainer on one machine, vLLM in a HF Space, the wordle env in another HF Space and weights going through a Hub Bucket. no shared cluster, just HTTPS
it works because ~99% of bf16 weights don't change between RL steps so you only sync the diff. 1.2 GB to 25 MB of payload per step
https://huggingface.co/blog/delta-weight-sync
what I like the most is the way it proves you can use the Hub for basically everything 🧐 → trainer on one machine, vLLM in a HF Space, the wordle env in another HF Space and weights going through a Hub Bucket. no shared cluster, just HTTPS
it works because ~99% of bf16 weights don't change between RL steps so you only sync the diff. 1.2 GB to 25 MB of payload per step
https://huggingface.co/blog/delta-weight-sync
sergiopaniego
posted an update 3 months ago
Post
2383
most multi-turn RL loops have a silent bug: you decode the model's output to detect tool calls, then re-tokenize the conversation for the next turn. BPE isn't invertible, so decode then re-encode can land on different ids. gradient ends up on tokens the model never sampled. no crash, just quietly wrong math and broken training
@qgallouedec wrote a super educational blog on MITO (message-in, token-out) vs TITO (token-in, token-out) and how you might fix the problem above
go read it 🤓
https://qgallouedec-tito.hf.space/
@qgallouedec wrote a super educational blog on MITO (message-in, token-out) vs TITO (token-in, token-out) and how you might fix the problem above
go read it 🤓
https://qgallouedec-tito.hf.space/
sergiopaniego
posted an update 3 months ago
Post
6335
new banger blog alert 🚨
@ariG23498 is starting a blog series about profiling in pytorch and part 1 just dropped
takes you from the simplest scenario to actually knowing what your gpu is doing. if you have never opened a profiler trace this is where you start
covers
find it here: https://huggingface.co/blog/torch-profiler
@ariG23498 is starting a blog series about profiling in pytorch and part 1 just dropped
takes you from the simplest scenario to actually knowing what your gpu is doing. if you have never opened a profiler trace this is where you start
covers
torch.profiler from scratch. reading tables and traces, overhead bound vs compute bound, the full dispatch chain from python to gpu kernels, and what torch.compile is actually fusing under the hoodfind it here: https://huggingface.co/blog/torch-profiler
- 1 reply