cd /news/artificial-intelligence/from-trajectories-to-prefixes-reusin… · home topics artificial-intelligence article
[ARTICLE · art-69615] src=arxiv.org ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

From Trajectories to Prefixes: Reusing Teacher Trajectories via Replayed Prefixes and Online Continuation

Researchers propose Prefix-GRPO, a reinforcement learning framework that improves small language model agents by decomposing teacher trajectories into replay-aligned prefix queries and online continuations, enabling more efficient learning in long-horizon environments. Experiments on TextCraft, BabyAI, and ALFWorld show that Prefix-GRPO outperforms distillation and standard RL baselines, with implementation available on GitHub.

read1 min views1 publishedJul 23, 2026

arXiv:2607.19395v1 Announce Type: new Abstract: Small language models are attractive backbones for interactive agents, but direct distillation from strong teacher trajectories often turns rich multi-turn behavior into one-shot imitation targets. This is inefficient in long-horizon environments, where early decisions shape later states and rewards. We propose Prefix-GRPO, a reinforcement learning framework that decomposes teacher trajectories into replay-aligned prefix queries and online continuations. Each prefix is replayed in the environment to recover a valid intermediate state, after which the student continues online interaction and receives task reward. Unlike response-only GRPO, Prefix-GRPO also applies clipped policy updates to historical assistant tokens inside the replayed prefix, using a policy-distilled SFT checkpoint to estimate their old log-probabilities. This unifies prefix learning and continuation learning within the same policy-optimization form. Experiments on TextCraft, BabyAI, and ALFWorld show that Prefix-GRPO improves small-model agents over distillation and standard RL baselines, while ablations show that replay alone is insufficient without explicit prefix-token optimization. The implementation and reproduction scripts are available at https://github.com/HappynessI/Prefix_GRPO.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @prefix-grpo 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/from-trajectories-to…] indexed:0 read:1min 2026-07-23 ·