Abstract:Post-training techniques combined with inference-time scaling significantly enhance the reasoning and alignment capabilities of large language models (LLMs). However, a fundamental tension arises: inference-time methods benefit from diverse sampling from a relatively flattened probability distribution, whereas reinforcement learning (RL)-based post-training inherently sharpens these distributions. To address this, we propose Exploration-Driven Optimization (EDO), which extends reward-biasing style exploration objectives to iterative post-training and integrates them into standard RL objectives, encouraging greater diversity in sampled solutions while facilitating more effective inference-time computation. We incorporate EDO into iterative Direct Preference Optimization (iDPO) and Group Relative Policy Optimization (GRPO), resulting in two variants: ED-iDPO and ED-GRPO. Extensive experiments demonstrate that both ED-iDPO and ED-GRPO exhibit greater solution diversity and improved reasoning abilities, particularly when combined with test-time computation techniques like self-consistency. Across three in-distribution reasoning benchmarks, EDO achieves a 1.0-1.3\% improvement over the strongest baselines, and delivers an additional 1.5\% average gain on five out-of-distribution tasks. Beyond accuracy, EDO preserves model entropy and stabilizes RL training dynamics, highlighting its effectiveness in preventing over-optimization collapse. Taken together, these results establish EDO as a practical framework for balancing exploration and exploitation in LLM reasoning, especially in settings that rely on test-time scaling.
| Comments: | Accepted by TMLR 2026 |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.09853 [cs.LG] |
| (or arXiv:2605.09853v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.09853 arXiv-issued DOI via DataCite (pending registration) |
From: Changhao Li [view email]
[v1]
Mon, 11 May 2026 01:10:48 UTC (381 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。