Open Models Almanac
Methodspost-trainingagentic post-training

general family · filed under post-training

Agentic reinforcement learning

Agentic reinforcement learning applies RL to multi-step agent tasks, where rollouts span multiple turns and dialogue contexts in an interactive environment.1,2 Because outcome rewards provide only coarse supervision for these long trajectories, it adopts an agent-centric execution model with fine-grained learning signals such as loss masking and advantage shaping.3

How this definition was written

Summarised by glm-5.3-flash from 1 source; every sentence is checked against the quote it cites.

  1. Agentic rollouts span multiple turns and dialogue contexts — MiMo V2 6 technical report
  2. scaling reinforcement learning (RL) on complex agentic tasks — MiMo V2 6 technical report
  3. outcome rewards provide only coarsesupervision. Wethereforeadoptanagent-centricexecutionmodelandorganizetrajectory data as a hierarchy. Within this hierarchy, a configurablePenalty Module applies loss masking 26 and advantage shaping — MiMo V2 6 technical report

Also called agentic RL, Large-scale agentic reinforcement learning.

sources
8
models
6
labs adopt it
3
strongest
core

Documented in

Evidence

8 quotes from 8 sources, one card per model, each opening with its strongest.

How sources treat it
used 6core 2

LFM3-1.7B

Liquid AIadopted3 sources

Post-training from this checkpoint (SFT, mixed RL, multi-domain on-policy distillation, and agentic RL) produces LFM3-1.7B.

usedpost trainingin LFM3-1.7BLiquid AI
2 more from this model

tasks from web browsing to office work are run inside real agent harnesses, preparing the model for deployment.

usedpost trainingin LFM3-1.7BLiquid AI

tasks from web browsing to office work are run inside real agent harnesses, preparing the model for deployment

usedpost trainingin LFM3-1.7BLiquid AI
↑