# LEAF: Growing Trees Without Branching for Speech-Aware Large Language Model Post-Training

arXiv: https://arxiv.org/abs/2606.07610 · HTML: https://mlsanity.com/paper/2606.07610/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning.
- Builds on 17 of its 35 references that are in the map.
- First posted on arXiv 29 May 2026.

## Placed in

- LLM reasoning / [Audio-language model reasoning](https://mlsanity.com/lr/audio-language-model-reasoning/)

## Builds on (most cited first, 17 of 17)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning](https://mlsanity.com/paper/2506.01939/) (2025)
- [VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation](https://mlsanity.com/paper/2101.00390/) (2021)
- [Large Language Models Are State-of-the-Art Evaluators of Translation Quality](https://mlsanity.com/paper/2302.14520/) (2023)
- [JudgeLM: Fine-tuned Large Language Models are Scalable Judges](https://mlsanity.com/paper/2310.17631/) (2023)
- [Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models](https://mlsanity.com/paper/2507.08128/) (2025)
- [VoiceBench: Benchmarking LLM-Based Voice Assistants](https://mlsanity.com/paper/2410.17196/) (2024)
- [VinePPO: Refining Credit Assignment in RL Training of LLMs](https://mlsanity.com/paper/2410.01679/) (2024)
- [On The Landscape of Spoken Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2504.08528/) (2025)
- [TreeRL: LLM Reinforcement Learning with On-Policy Tree Search](https://mlsanity.com/paper/2506.11902/) (2025)
- [DailyTalk: Spoken Dialogue Dataset for Conversational Text-to-Speech](https://mlsanity.com/paper/2207.01063/) (2022)
- [TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling](https://mlsanity.com/paper/2508.17445/) (2025)
- [M-Prometheus: A Suite of Open Multilingual LLM Judges](https://mlsanity.com/paper/2504.04953/) (2025)
- [Granite-speech: open-source speech-aware LLMs with strong English ASR capabilities](https://mlsanity.com/paper/2505.08699/) (2025)
- [Exploiting Tree Structure for Credit Assignment in RL Training of LLMs](https://mlsanity.com/paper/2509.18314/) (2025)
- [Group Relative Policy Optimization for Speech Recognition](https://mlsanity.com/paper/2509.01939/) (2025)
- [Advancing Speech Understanding in Speech-Aware Language Models with GRPO](https://mlsanity.com/paper/2509.16990/) (2025)

## Abstract (arXiv)

State-of-the-art GRPO-style methods for speech-aware large language model post-training suffer from coarse credit assignment, broadcasting the same terminal-reward advantage to every token in a response. This ignores useful structure within rollout batches, where speech-conditioned completions often share prefixes before diverging at important decisions. We propose Low-rank Exploration with Adaptive Forking (LEAF), a retrospective tree-based RL method that recovers this structure without online branching or additional decoding. LEAF samples complete responses, selects high-surprisal boundaries, groups responses by shared prefixes, and assigns span-level advantages using descendant rewards. We theoretically justify LEAF's span-level credit assignment and boundary-selection design. Empirically, LEAF improves over GRPO across speech question answering and speech translation benchmarks under the same rollout and low-rank adaptation budget. Notably, smaller LEAF-trained models consistently outperform current state-of-art, full-parameter baselines.