# Where Should RL Post-Training Compute Go? Model Size, Search, Learning, and Feedback

arXiv: https://arxiv.org/abs/2607.13389 · HTML: https://mlsanity.com/paper/2607.13389/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 18 references that are in the map.
- First posted on arXiv 15 Jul 2026.

## Builds on (most cited first, 18 of 18)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [The Art of Scaling Reinforcement Learning Compute for LLMs](https://mlsanity.com/paper/2510.13786/) (2025)
- [Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning](https://mlsanity.com/paper/2509.25300/) (2025)

## Built on by (most cited first, 2 of 2)

- [FSPO: Policy-Consistent Risk and Pareto-Feasible Control for Budgeted LLM RL Post-Training](https://mlsanity.com/paper/2610.02828/) (2026)
- [Do Small Language Models Learn to Negotiate? A Controlled Scaling Study of RL-Trained Sellers](https://mlsanity.com/paper/2610.06204/) (2026)

## Abstract (arXiv)

Reinforcement Learning (RL) post-training is increasingly used to adapt foundation models for reasoning, planning, and feedback-driven robot-learning pipelines, but constrained post-training resources are often summarized by a single total FLOP budget. We study the fixed-budget decision problem behind this practice: under the same post-training budget, should one use a larger policy, train a smaller policy longer, generate more rollout search, or spend compute on stronger reward feedback? We introduce a FLOP-accounting framework for GRPO post-training that decomposes compute into rollout/search, policy-update/learning, and reward- or feedback-model evaluation. Across LoRA-adapted Qwen2.5 policies, we find conditional allocation frontiers: the best observed allocation changes with model size, compute budget, reward system, and evaluation target. Same-FLOP model-size comparisons show that model choice and training allocation are coupled because larger policies consume more per-token compute and therefore buy fewer updates or rollouts under the same budget. Reward systems also change the accounting: rule-based rewards spend nearly all non-update compute on policy rollouts, while PRM-style feedback allocates a visible part of the budget to reward-model inference. We present RACE as a diagnostic pilot-grid protocol, not a guarantee of held-out improvement, for identifying allocation regimes before expensive validation runs; our results suggest that RL post-training papers should report total FLOPs together with how compute is divided among model size, search, learning, and feedback.