pith. sign in

Title resolution pending

LlamaRL: A Distributed Asynchronous Reinforcement Learning Framework for Efficient Large-scale LLM Training , author= · 2025

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

Title metadata for this work has not finished resolving. The hub is built from the citation graph; the title resolver retries DOI and OpenAlex on its next pass.

fields

cs.DC 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

MARLaaS: Multi-Tenant Asynchronous Reinforcement Learning as a Service

cs.DC · 2026-05-08 · unverdicted · novelty 6.0

MARLaaS enables concurrent RL fine-tuning across up to 32 tasks using LoRA adapters and a disaggregated asynchronous architecture, matching single-task performance while improving accelerator utilization by 4.3x and cutting end-to-end time by 85%.

citing papers explorer

Showing 1 of 1 citing paper.

  • MARLaaS: Multi-Tenant Asynchronous Reinforcement Learning as a Service cs.DC · 2026-05-08 · unverdicted · none · ref 32

    MARLaaS enables concurrent RL fine-tuning across up to 32 tasks using LoRA adapters and a disaggregated asynchronous architecture, matching single-task performance while improving accelerator utilization by 4.3x and cutting end-to-end time by 85%.