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.
arXiv preprint arXiv:2511.16108(2025)
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 11roles
background 3polarities
background 3representative citing papers
ECHO is a hybrid RL objective that trains agents to predict environment observation tokens from their actions, doubling GRPO pass@1 on TerminalBench-2.0 while improving dynamics prediction on held-out trajectories.
ReBel uses belief-consistency supervision and belief-aware grouping to improve credit assignment in long-horizon RL for LLM agents, achieving up to 20.4 percentage points higher success and 2.1x better sample efficiency than GRPO on ALFWorld and WebShop.
Dynamic Gradient Gating monitors lm_head gradient norms to safely reuse rollout batches in RLVR, achieving up to 2.93x sample efficiency and 2.14x wall-clock speedup across math, ALFWorld, WebShop, and QA tasks.
DAgger-style training with turn-level policy interpolation raises 4B and 8B LLM agents to 27.3% and 29.8% on SWE-bench Verified, beating several larger published systems.
ROSE is a system for cooperative elasticity that co-locates serving and rollout models on shared GPUs, delivering 1.3-3.3x higher end-to-end throughput than fixed-resource baselines while preserving serving SLOs.
Terminus-4B, a Qwen3-4B post-trained with SFT and rubric-based GRPO, matches or beats frontier models as a terminal-execution subagent while cutting main-agent tokens ~30% on SWE-Bench-style tasks.
A two-stage SFT pipeline distills execution-free then execution-based trajectories from a 480B model into smaller Qwen2.5-Coder agents, yielding 62.2% resolution on SWE-bench Verified and 44.1% zero-shot on the multilingual version.
APPO improves LLM agent training by branching at tokens selected for both uncertainty and future impact, then scaling credit for consequential reasoning procedures.
f-OPD decomposes on-policy distillation drift into rollout and supervision components, then applies a sample-level freshness score to adaptively limit stale data influence and stabilize long-horizon agent training.
Comparative study of four execution substrates for coding-agent RL rollouts finds 110x cold-start latency variation and 1.8x spread in worker-hours for one million 150-step trajectories.
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.
-
ECHO: Terminal Agents Learn World Models for Free
ECHO is a hybrid RL objective that trains agents to predict environment observation tokens from their actions, doubling GRPO pass@1 on TerminalBench-2.0 while improving dynamics prediction on held-out trajectories.
-
Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents
ReBel uses belief-consistency supervision and belief-aware grouping to improve credit assignment in long-horizon RL for LLM agents, achieving up to 20.4 percentage points higher success and 2.1x better sample efficiency than GRPO on ALFWorld and WebShop.
-
When to Stop Reusing: Dynamic Gradient Gating for Sample-Efficient RLVR
Dynamic Gradient Gating monitors lm_head gradient norms to safely reuse rollout batches in RLVR, achieving up to 2.93x sample efficiency and 2.14x wall-clock speedup across math, ALFWorld, WebShop, and QA tasks.
-
Revisiting DAgger in the Era of LLM-Agents
DAgger-style training with turn-level policy interpolation raises 4B and 8B LLM agents to 27.3% and 29.8% on SWE-bench Verified, beating several larger published systems.
-
ROSE: Rollout On Serving GPUs via Cooperative Elasticity for Agentic RL
ROSE is a system for cooperative elasticity that co-locates serving and rollout models on shared GPUs, delivering 1.3-3.3x higher end-to-end throughput than fixed-resource baselines while preserving serving SLOs.
-
Terminus-4B: Can a Smaller Model Replace Frontier LLMs at Agentic Execution Tasks?
Terminus-4B, a Qwen3-4B post-trained with SFT and rubric-based GRPO, matches or beats frontier models as a terminal-execution subagent while cutting main-agent tokens ~30% on SWE-Bench-style tasks.
-
From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents
A two-stage SFT pipeline distills execution-free then execution-based trajectories from a 480B model into smaller Qwen2.5-Coder agents, yielding 62.2% resolution on SWE-bench Verified and 44.1% zero-shot on the multilingual version.
-
APPO: Agentic Procedural Policy Optimization
APPO improves LLM agent training by branching at tokens selected for both uncertainty and future impact, then scaling credit for consequential reasoning procedures.
-
$\boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control
f-OPD decomposes on-policy distillation drift into rollout and supervision components, then applies a sample-level freshness score to adaptively limit stale data influence and stabilize long-horizon agent training.
-
The Rollout Infrastructure Tax in Coding-Agent Reinforcement Learning
Comparative study of four execution substrates for coding-agent RL rollouts finds 110x cold-start latency variation and 1.8x spread in worker-hours for one million 150-step trajectories.