Towards Robust Reinforcement Learning for Small-Scale Language Model Agents

Md. Rezwanul Haque Md. Milon Islam Fakhri Karray

Jul 2026 · arXiv.org · Vol abs/2607.25091 · 0 citations · 26 references

Computer Science Mathematics

TL;DR

A capacity-headroom hypothesis is proposed, which states that PPO performance at the SLM scale depends on both a fluent supervised model and a discriminative reward signal, rather than on the number of model parameters.

Abstract

The alignment of Small Language Models (SLMs) in the 70--500M parameter range using reinforcement learning is often considered unstable, though the underlying failure mechanisms have not been systematically investigated. In the State-of-the-Art (SOTA) research, fifteen (model, corpus) configurations were trained using Proximal Policy Optimization (PPO). The experiments included Pythia-70M, 160M, 410M and SmolLM2-135M, 360M on the TinyStories, CNN/DailyMail, and Wikitext-103 corpora. Three reproducible failure modes were identified in small-scale language models: silent LoRA parameter freezing in standard PEFT/TRL pipelines, numerical overflow in importance ratios when using bfloat16, and catastrophic policy collapse due to reward-model error. These issues were addressed using a merge-and-reinitialize adapter technique, float32 precision during PPO updates, and a three-layer safety mechanism comprising reward whitening, importance-ratio guarding, and weight rollback. In this paper, a capacity-headroom hypothesis is proposed, which states that PPO performance at the SLM scale depends on both a fluent supervised model ($\text{PPL}<20$) and a discriminative reward signal, rather than on the number of model parameters. The proposed system converged stably in all experiments and improved preference win rate over the SFT baseline in configurations with a fluent prior and an informative reward signal. Furthermore, it outperformed instruction-tuned baselines while requiring significantly less training data. All checkpoints, preference datasets, and training scripts are publicly released$^{\S}$.

DOI arXiv Semantic Scholar

View source

Similar papers

Review Open access Aug 2026

Reinforcement Learning in the Era of Large Language Models: Challenges and Opportunities

A systematic literature review on how RL are adapted and scaled as a fundamental post-training tools and how innovations in the RL pipeline enhance the domain-specific LLMs is conducted.

Qianyue Hao, Lin Chen, Xiao-Qian Qi et al. · ACM Computing Surveys · 1 citation

#machine learning Preprint Aug 2026

Demystifying Reinforcement Learning Post-Training of Language Models

This work deconstructs the RL post-training algorithm, investigating each step to clarify what is actually happening beneath the surface, and uses the entropy of the policy's output distribution as a lens to compare the distributions learned through pretraining, SFT, and RL post-training, revealing how each stage shapes model certainty.

D. Clay, Saket Gollapudi, Sankar V Harilal et al. · 0 citations

Preprint Jul 2026

Cross-Benchmark Generalization in Long-Horizon Agents

Desc descriptive evidence is provided that long-horizon multi-tool post-training can change ways of working that transfer beyond its training domain, and both software-engineering benchmarks improve despite the training collection containing no software-engineering tasks.

Sushant Mehta, Logan Ritchie, Liudas Panavas et al. · 0 citations

Book Open access Aug 2026

Large Language Model (LLM) as an Excellent Reinforcement Learning Researcher in both Single-Agent and Multi-Agent Scenarios

In the quantitative finance area, particularly in order execution, reinforcement learning (RL) has shown great promise due to its ability to interact with market environments based on real data. However, traditional RL methods suffer from slow research speed and rely on static market assumptions, which do not consider the impact of the agent's execution action on the environment. To address these, we propose a Self-Evolutional single-agent/multi-agent Reinforcement Learning (SE-RL) framework. The framework utilizes a Large Language Model (LLM) to design various RL algorithm modules, such as agent model design, reward function, profiling, communication, and state imagination, by leveraging the LLM generating module output or code. SE-RL could continuously improve the accuracy of LLM-generated RL algorithms through a dual-enhancement kit at both high-level (prompt refinement) and low-level (parameter fine-tuning). Additionally, we use a multi-agent system to simulate dynamic financial markets, accounting for the impact of order executions on market dynamics. To further enhance training in such a dynamic market, we develop a hybrid environment training method that could rebalance each environment's loss weight. Comprehensive experiments on 200 realistic stock datasets demonstrate that our proposed framework outperforms current state-of-the-art baselines. Project page: https://kdd2026-se-rl.github.io/.

Vincent Fu, Xin-Xin Xu, Weichen Xu et al. · Proceedings of the 32nd ACM... · 0 citations

Jul 2026

Distilled Reinforcement Learning for LLM Post-training

Extensive experiments show that Distilled RL substantially outperforms standard RL and OPD in terms of both pass@1 and pass@k, and can effectively transfer previously unavailable knowledge from a teacher model to a student model.

Chen Wang, Zhaochun Li, Jionghao Bai et al. · arXiv.org · 2 citations

Preprint Aug 2026

Learning Generalizable Behaviors for Terminal Agents

River, a simple training recipe that improves reward quality by filtering low-quality environments and augmenting outcome rewards with process-level behavior regularization is proposed, which achieves the best performance among evaluated open-source RL-trained 8B models across four terminal-agent benchmarks.

Yi-Fan Yao, Bo Pang, Xuan-Phi Nguyen et al. · 1 citation