# New papers question what reinforcement learning guidance, backdoor leaderboards and summary-tree retrieval actually measure

One paper gives a bias-variance theory of when external guidance helps reinforcement learning with verifiable rewards, another says backdoor-defense costs require a never-poisoned control model, and a third retests RAPTOR-style trees at matched cost.

- Published: 2026-10-07T06:04:58.881Z
- Canonical: https://polylog.news/ai/2026-10-07/new-papers-question-what-reinforcement-learning-guidance-bac
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [arXiv cs.LG (Guidance-Augmented GRPO)](https://arxiv.org/abs/2610.06861), [arXiv cs.CR (TARE)](https://arxiv.org/abs/2610.06994), [arXiv cs.CL (Tree Navigation)](https://arxiv.org/abs/2610.06902)

Three of Tuesday's arXiv postings are about measurement more than new methods. Each argues that a common comparison in its subfield confounds two effects. The first paper addresses reasoning post-training. Reinforcement learning with verifi…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-10-07/new-papers-question-what-reinforcement-learning-guidance-bac (subscription information: https://polylog.news/pricing).