taxonomy node · level 2

agentic post-training

31 methods filed at this node or below it, from the sources of 14 models.

post-training :: agentic post-training

Matching aids for the classifier: agentic reinforcement learning; multi-environment RLVR; tool-integrated reasoning training; multi-turn collaboration simulator.

By model

Which of this branch's techniques each model's own documents describe, and how strongly. Under each model: its strongest treatment anywhere in the branch.

Model	techniques
DeepSeek-V4.1-Flash used	Repair-agent environment correction loop usedRepercussion signal for agent-crashed environments used—
DeepSeek-V4-Flash-0731 used	Re-post-training for agentic capabilities used—
NVIDIA-Nemotron-3-Ultra-550B-A55B used	Concurrent multi-environment post-training usedMulti-environment reinforcement learning from verifiable rewards used—
MiMo-V2.6-Flash core	Agentic reinforcement learning coreContainer-level network isolation usedEnvironment hardening usedEnvironment preparation to prevent solution leakage usedMulti-harness training usedUnified trajectory representation for agentic reinforcement learning used—
MiMo-V2.5 used	Agentic post-training usedAgentic reinforcement learning used—
GLM-5.3 used	Environment scaling for realistic training tasks used—
MiniMax-M3 used	Multi-turn collaboration simulator used—
DeepSeek-V3.2 used	Generate-verify-refine loop usedReinforcement learning on synthetic agentic data usedTraining agentic policies with real-world tools usedReinforcement learning restricted to search and code environments evaluated—
Kimi K3 core	Training on verifiable problems in agentic environments coreAutonomous Execution Tasks (AET) usedMock applications for personal-assistant reinforcement learning usedUnified white-box reinforcement-learning environment used—
Laguna-S-2.1 core	Production-harness-matched reinforcement learning coreReinforcement learning in an agent harness coreMulti-harness trajectory training with native behavior preservation usedSeed-based terminal task generation used—
MiMo-V2.5-Pro used	Agentic post-training usedAgentic reinforcement learning used—
MiMo-V2.6-Pro core	Agentic reinforcement learning coreContainer-level network isolation usedEnvironment hardening usedEnvironment preparation to prevent solution leakage usedMulti-agent task decomposition and coordination usedMulti-harness training usedUnified trajectory representation for agentic reinforcement learning used—
NVIDIA-Nemotron-3.5-Lightning-30B-A3B core	Multi-environment reinforcement learning coreHarness-optimized training used—
gpt-oss-120b used	Agentic tool-use training usedPython tool use in chain-of-thought used—

agentic post-training

In this branch 31

filed here 31

By model