AstraFlow decouples RL components into autonomous dataflow services to natively support multi-policy agentic LLM training, elastic scaling, and cross-region execution with 2.7x speedup on math, code, search, and AgentBench workloads.
Agentrl: Scaling agentic reinforcement learning with a multi-turn, multi-task framework
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 12roles
background 1polarities
background 1representative citing papers
G2PO transforms linear trajectories into graphs, aggregates identical states for lower-variance value estimates, and uses edge-centric TD standardization, reporting up to 22.2% gains over GRPO on WebShop, ALFWorld, and AppWorld.
AgenticRL deploys a multimodal GPT agent in a closed-loop process to autonomously design and refine reward functions for PPO-trained vision-conditioned UAV navigation policies, reporting 71% policy improvement and 91% real-world success.
AnomalyAgent uses tool-augmented reinforcement learning with self-reflection to generate realistic industrial anomalies, achieving better metrics than zero-shot methods on MVTec-AD.
TRACE identifies capability gaps from agent trajectory contrasts, synthesizes per-capability RL training environments, and routes LoRA adapters at inference to improve performance on customer service and tool-use benchmarks.
SABER uses a trained ReAct agent to produce bounded adversarial edits to robot instructions, cutting task success by 20.6% and increasing execution length and violations on the LIBERO benchmark across six VLA models.
AgentIAD introduces an agentic VLM with Perceptive Zoomer, Web Searcher, and Comparative Retriever tools plus two-stage SFT-then-RL training, achieving 5.92% higher classification accuracy than prior SOTA on the MMAD benchmark.
Tree Training serializes tree trajectories via DFS and uses redundancy-free partitioning to compute weighted per-token losses exactly once per token, achieving up to 6.2x training speedup on dense and MoE models.
AlphaMemo equips LLM alpha-mining agents with AST-diff motif memory, residual learning, and asymmetric veto control to improve out-of-sample factor discovery on CSI 500 and S&P 500.
GROW decomposes trajectories into state-action samples to enable GRPO for multi-turn VLM agents and reports state-of-the-art results on more than 800 Minecraft tasks.
Skill1 trains a single RL policy to co-evolve skill selection, utilization, and distillation in language model agents from one task-outcome reward, using low-frequency trends to credit selection and high-frequency variation to credit distillation, outperforming baselines on ALFWorld and WebShop.
Gated synthetic augmentations can substitute for additional human-authored RLVR tasks at a cost-adjusted trade rate of 1.4x-11.6x while retaining held-out generalization on ten benchmarks spanning code, instruction following, reasoning, and agentic function calling.
citing papers explorer
-
AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs
AstraFlow decouples RL components into autonomous dataflow services to natively support multi-policy agentic LLM training, elastic scaling, and cross-region execution with 2.7x speedup on math, code, search, and AgentBench workloads.
-
Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning
G2PO transforms linear trajectories into graphs, aggregates identical states for lower-variance value estimates, and uses edge-centric TD standardization, reporting up to 22.2% gains over GRPO on WebShop, ALFWorld, and AppWorld.
-
AgenticRL: Self-Refining Agentic Reinforcement Learning for Vision-Conditioned UAV Navigation
AgenticRL deploys a multimodal GPT agent in a closed-loop process to autonomously design and refine reward functions for PPO-trained vision-conditioned UAV navigation policies, reporting 71% policy improvement and 91% real-world success.
-
AnomalyAgent: Agentic Industrial Anomaly Synthesis via Tool-Augmented Reinforcement Learning
AnomalyAgent uses tool-augmented reinforcement learning with self-reflection to generate realistic industrial anomalies, achieving better metrics than zero-shot methods on MVTec-AD.
-
TRACE: Capability-Targeted Agentic Training
TRACE identifies capability gaps from agent trajectory contrasts, synthesizes per-capability RL training environments, and routes LoRA adapters at inference to improve performance on customer service and tool-use benchmarks.
-
SABER: A Stealthy Agentic Black-Box Attack Framework for Vision-Language-Action Models
SABER uses a trained ReAct agent to produce bounded adversarial edits to robot instructions, cutting task success by 20.6% and increasing execution length and violations on the LIBERO benchmark across six VLA models.
-
AgentIAD: Agentic Industrial Anomaly Detection via Adaptive Memory Augmentation
AgentIAD introduces an agentic VLM with Perceptive Zoomer, Web Searcher, and Comparative Retriever tools plus two-stage SFT-then-RL training, achieving 5.92% higher classification accuracy than prior SOTA on the MMAD benchmark.
-
Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse
Tree Training serializes tree trajectories via DFS and uses redundancy-free partitioning to compute weighted per-token losses exactly once per token, achieving up to 6.2x training speedup on dense and MoE models.
-
AlphaMemo: Structured Search-Process Memory for Self-Evolving Alpha Mining Agents
AlphaMemo equips LLM alpha-mining agents with AST-diff motif memory, residual learning, and asymmetric veto control to improve out-of-sample factor discovery on CSI 500 and S&P 500.
-
GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents
GROW decomposes trajectories into state-action samples to enable GRPO for multi-turn VLM agents and reports state-of-the-art results on more than 800 Minecraft tasks.
-
Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
Skill1 trains a single RL policy to co-evolve skill selection, utilization, and distillation in language model agents from one task-outcome reward, using low-frequency trends to credit selection and high-frequency variation to credit distillation, outperforming baselines on ALFWorld and WebShop.
-
Trading Human Curation for Synthetic Augmentation in RLVR
Gated synthetic augmentations can substitute for additional human-authored RLVR tasks at a cost-adjusted trade rate of 1.4x-11.6x while retaining held-out generalization on ten benchmarks spanning code, instruction following, reasoning, and agentic function calling.