Techniquespost-trainingagentic post-training

implementation detail · filed under post-training

Reinforcement learning restricted to search and code environments

A reinforcement-learning setup that limits training to search and code environments.

Also called RL only in search and code environments.

source: 1
model: 1
labs adopt it: 0
strongest: evaluated

How sources treat it

One count per evidence span, weakest treatment to strongest.

evaluated 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

DeepSeek-V3.2-Exp is trained with RL only in search and code environments.

evaluatedoptimizationin DeepSeek-V3.2-ExpDeepSeek

paper·DeepSeek

Filed alongside

Other methods under post-training :: agentic post-training.

Agentic reinforcement learning Multi-harness training Agentic tool-use training Environment hardening Reinforcement learning on synthetic agentic data Repair-agent environment correction loop Agentic post-training Autonomous Execution Tasks (AET)Concurrent multi-environment post-training Container-level network isolation Environment preparation to prevent solution leakage Environment scaling for realistic training tasks Generate-verify-refine loop Harness-optimized training Mock applications for personal-assistant reinforcement learning Multi-agent task decomposition and coordination Multi-environment reinforcement learning Multi-environment reinforcement learning from verifiable rewards Multi-harness trajectory training with native behavior preservation Multi-turn collaboration simulator Production-harness-matched reinforcement learning Python tool use in chain-of-thought Re-post-training for agentic capabilities Reinforcement learning in an agent harness