SAGC dynamically adjusts group sizes in synchronous GRPO and DAPO via online constrained optimization to cut stragglers, improve wall-clock speed, and maintain or improve rewards and downstream reasoning performance.
arXiv preprint arXiv:2508.02833 , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
FGRPO decentralizes GRPO fine-tuning via adaptive aggregation based on relative performance gain to achieve robust convergence on non-IID data while preserving privacy.
LC-ERD frames LLM self-alignment as latent structure mining via a Variational Logic Potential and Multi-Agent Value Decomposition to provide granular, logic-consistent supervision.
Waypoint-based bi-level planning with curriculum RLVR improves multi-robot task success rates in dense-obstacle benchmarks over motion-agnostic and VLA baselines.
citing papers explorer
-
Faster Synchronous On-Policy RL via Straggler-Aware Group Sizing
SAGC dynamically adjusts group sizes in synchronous GRPO and DAPO via online constrained optimization to cut stragglers, improve wall-clock speed, and maintain or improve rewards and downstream reasoning performance.
-
FGRPO: Federated GRPO with Adaptive Aggregation on Non-IID Data
FGRPO decentralizes GRPO fine-tuning via adaptive aggregation based on relative performance gain to achieve robust convergence on non-IID data while preserving privacy.
-
LC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward Decomposition
LC-ERD frames LLM self-alignment as latent structure mining via a Variational Logic Potential and Multi-Agent Value Decomposition to provide granular, logic-consistent supervision.
-
Navigating the Clutter: Waypoint-Based Bi-Level Planning for Multi-Robot Systems
Waypoint-based bi-level planning with curriculum RLVR improves multi-robot task success rates in dense-obstacle benchmarks over motion-agnostic and VLA baselines.