Scheduling Your LLM Reinforcement Learning with Reasoning Trees

arXiv:2510.24832v2 Announce Type: replace Abstract: Using Reinforcement Learning with Verifiable Rewards (RLVR) to optimize Large Language Models (LLMs) can be conceptualized as progressively editing a query's `Reasoning Tree'. This process involves exploring nodes (tokens) and dynamically modifying the model's policy at each node. When combined with data scheduling, this process yields further gains in data efficiency and accuracy. However, existing RLVR data scheduling methods typically rely on path-based metrics to rank queries, overlooking the reasoning tree structures of these queries. In this paper, we introduce a novel metric, namely Reasoning Score (r-score), which measures the query's learning difficulty based on the structure of its reasoning tree. Based on the r-score, we propose the Reasoning Tree Schedule (Re-Schedule), a scheduling algorithm that constructs a curriculum progressing from structurally simple (high r-score) to complex (low r-score) queries. Experiments on six math-reasoning benchmarks show that Re-Schedule significantly improves average accuracy, achieving gains of up to 3.2%. These strong results validate our approach and demonstrate that a structural understanding of the reasoning tree provides a more powerful and principled foundation for RLVR data scheduling.

Related

• Rethinking Token-Level Credit Assignment in RLVR: A Polarity-Entropy Analysis
• GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning
• How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization
• Does RLVR Extend Reasoning Boundaries? Investigating Capability Expansion in Vision-Language Models
• Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning
• SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks

Source: arXiv cs.AI | 2026-04-28