specific method · filed under post-training
Unified trajectory representation for agentic reinforcement learning
A unified representation of agent trajectories used to refine the learning signal.
Also called unified trajectory representation.
- source
- 1
- models
- 2
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
we design a unified trajectory representation and a penalty mechanism that together refine the learning signal
usedsoftware implementationin MiMo-V2.6 RL infrastructureXiaomi
Filed alongside
Other methods under post-training :: agentic post-training.
Agentic reinforcement learningMulti-harness trainingAgentic tool-use trainingEnvironment hardeningReinforcement learning on synthetic agentic dataRepair-agent environment correction loopAgentic post-trainingAutonomous Execution Tasks (AET)Concurrent multi-environment post-trainingContainer-level network isolationEnvironment preparation to prevent solution leakageEnvironment scaling for realistic training tasksGenerate-verify-refine loopHarness-optimized trainingMock applications for personal-assistant reinforcement learningMulti-agent task decomposition and coordinationMulti-environment reinforcement learningMulti-environment reinforcement learning from verifiable rewardsMulti-harness trajectory training with native behavior preservationMulti-turn collaboration simulatorProduction-harness-matched reinforcement learningPython tool use in chain-of-thoughtRe-post-training for agentic capabilitiesReinforcement learning in an agent harness