EPS
← All batches·2605.15726

Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR

topic: current_projecttop score: 100released: 2026-05-19first surfaced: 2026-05-18arXivPDFthreats2026-05-182026-05-19

Authors: Chanuk Lee, Sangwoo Park, Minki Kang et al.

arXiv · PDF

Summary

arXiv:2605. 15726v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a scalable paradigm for improving the reasoning capabilities of large language models.

Relevance

Read next because Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns ..., vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: code, text, line, rate, control, without, contexts, lora. Source: arxiv cs.AI (Artificial Intelligence).

Threat model

Potential threat/caveat for clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns ..., vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)": this item discusses benchmark.

Abstract

arXiv:2605.15726v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a scalable paradigm for improving the reasoning capabilities of large language models. However, its effectiveness is fundamentally limited by exploration: the policy can only improve on trajectories it has already sampled. While increasing the number of rollouts alleviates this issue, such brute-force scaling is computationally expensive, and existing approaches that modify the optimization objective provide limited control over what is explored. In this work, we propose NudgeRL, a framework for structured and diversity-driven exploration in RLVR. Our approach introduces Strategy Nudging, which conditions each rollout on lightweight, strategy-level contexts to induce diverse reasoning trajectories without relying on expensive oracle supervision. To effectively learn from such structured exploration, we further propose a unified objective, which decomposes the reward signal into inter- and intra-context components and incorporates a distillation objective to transfer discovered behaviors back to the base policy. Empirically, NudgeRL outperforms standard GRPO with up to 8 times larger rollout budgets, while outperforming oracle-guided RL baseline on average across five challenging math benchmarks. These results demonstrate that structured, context-driven exploration can serve as an efficient and scalable alternative to both brute-force rollout scaling and feasibility-oriented methods based on privileged information. Our code is available at https://github.com/tally0818/NudgeRL.