cd /news/machine-learning/rods-reward-driven-online-data-synth… · home topics machine-learning article
[ARTICLE · art-32067] src=arxiv.org ↗ pub= topic=machine-learning verified=true sentiment=· neutral

RODS: Reward-Driven Online Data Synthesis for Multi-Turn Tool-Use Agents

Researchers propose RODS (Reward-driven Online Data Synthesis) to address the depletion of informative samples in multi-turn tool-use reinforcement learning. RODS uses progress reward variance as a boundary detector to continuously synthesize new training samples, achieving comparable performance to a 17K-sample offline pipeline with roughly 20x fewer trajectories.

read1 min views2 publishedJun 18, 2026

arXiv:2606.19047v1 Announce Type: new Abstract: Multi-turn tool-use RL is bottlenecked by the rapid depletion of informative samples in static datasets. We observe that the gradient signal in GRPO concentrates on tasks with the highest rollout reward variance, a consequence of the Popoviciu upper bound. Consequently, samples near the agent's capability boundary -- where successes and failures are roughly balanced -- contribute disproportionately large policy gradients. As training progresses, this boundary continuously shifts, which gradually depletes the pool of informative samples in a static dataset. We propose RODS (Reward-driven Online Data Synthesis) to resolve this depletion. RODS closes the loop between RL training and data generation by repurposing the progress reward variance as a practical, zero-cost boundary detector that requires no extra inference beyond the rollouts already computed for training. It continuously identifies such boundary samples, synthesizes new multi-turn variants matching their structural complexity (e.g., API topology and dependency depth) via a skill-aligned resampling pipeline, and manages a dynamic replay buffer that co-evolves with the policy. Starting from 400 human seeds and maintaining an active training pool of ~800 samples, RODS achieves comparable performance to a 17K-sample offline pipeline while requiring roughly 20x fewer trajectories, and improves over fixed-data RL and environment augmentation in our controlled setting.

── more in #machine-learning 4 stories · sorted by recency
── more on @rods 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/rods-reward-driven-o…] indexed:0 read:1min 2026-06-18 ·