LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL

• URL: http://arxiv.org/abs/2607.04412v1
• Date: Sun, 05 Jul 2026 17:05:13 GMT
• Title: LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL
• Abstract summary: Reinforcement learning for non-verifiable instruction relies on judges with prompt-specific rubrics as reward signals.<n>While recent methods adapt these rubrics to the evolving policy during training, the training prompts themselves remain static.<n>This static approach often results in a critical misalignment between prompt difficulty and policy capability, leaving the judge unable to recover a discriminative reward signal.
• Score: 64.4276583943816
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning (RL) for non-verifiable instruction following increasingly relies on LLM judges with prompt-specific rubrics as reward signals. While recent methods adapt these rubrics to the evolving policy during training, the training prompts themselves remain static, drawn from fixed corpora. This static approach often results in a critical misalignment between prompt difficulty and policy capability, leaving the judge unable to recover a discriminative reward signal when prompts fail to elicit quality variance among rollouts. To address this misalignment, we introduce LLM-as-a-Tutor, a framework that extends the LLM's role from judge to tutor: a single model serves as an examiner that pairwise-compares policy rollouts to detect non-challenging prompts, and as a generator that appends atomic constraints to them. This append-only design monotonically raises difficulty in step with the policy's capability, producing a self-calibrating training signal without external difficulty schedules. On three complex instruction-following benchmarks, our method consistently outperforms both policy-unaware baselines and prior policy-adaptive methods that adapt rubrics or rewrite prompts, suggesting prompt adaptation as a missing axis of policy-awareness in non-verifiable RL.

Related papers

• Enhancing Rubric-based RL via Self-Distillation [23.111278687216544]
  We propose Criterion-Distilled Policy Optimization (CriPO), which enhances rubric-based RL via on-policy self-distillation.<n>CriPO consistently outperforms rubric-based RL, achieving stronger final performance with approximately $2times$ fewer optimization steps.
  arXiv  Detail & Related papers  (2026-07-20T15:50:02Z)
• Feedback Manipulation Regularization: Enabling Offline Agent Alignment for Imitation Learning [1.6038757247653772]
  Reinforcement learning (RL) research has increasingly shifted focus towards alignment, ensuring agents learn behaviors adhering to human values.<n>We propose Feedback Manipulation Regularization (FMR), an algorithm-agnostic method that harnesses evaluative feedback as a corrective signal to improve the alignment of imitation learning policies.<n>We adapt Safety Gymnasium environments to be a principled testbed for alignment evaluation, demonstrating improved aptitude and up to a 98% reduction in misalignment across a range of imitation learning algorithms.
  arXiv  Detail & Related papers  (2026-07-08T18:47:29Z)
• Stabilizing Reinforcement Learning with LLMs: Formulation and Practices [61.361819972410046]
  We show why and under what conditions the true sequence-level reward can be optimized via a surrogate token-level objective in policy gradient methods such as REINFORCE.<n>This insight provides a principled explanation for the crucial role of several widely adopted techniques in stabilizing RL training.
  arXiv  Detail & Related papers  (2025-12-01T07:45:39Z)
• One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy Gradient [16.05489579792086]
  We introduce one-token rollout (OTR), a novel fine-tuning algorithm that guides SFT with the policy gradient method.<n>OTR reframes the autoregressive learning process by treating each token generation as a single-step reinforcement learning trajectory.<n>Our findings establish OTR as a powerful and practical alternative for fine-tuning LLMs.
  arXiv  Detail & Related papers  (2025-09-30T14:25:56Z)
• LLM-Guided Reinforcement Learning: Addressing Training Bottlenecks through Policy Modulation [7.054214377609925]
  Reinforcement learning (RL) has achieved notable success in various domains.<n>Training effective policies for complex tasks remains challenging.<n>Existing approaches to mitigate training bottlenecks fall into two categories.
  arXiv  Detail & Related papers  (2025-05-27T03:40:02Z)
• Projected Off-Policy Q-Learning (POP-QL) for Stabilizing Offline Reinforcement Learning [57.83919813698673]
  Projected Off-Policy Q-Learning (POP-QL) is a novel actor-critic algorithm that simultaneously reweights off-policy samples and constrains the policy to prevent divergence and reduce value-approximation error. In our experiments, POP-QL not only shows competitive performance on standard benchmarks, but also out-performs competing methods in tasks where the data-collection policy is significantly sub-optimal.
  arXiv  Detail & Related papers  (2023-11-25T00:30:58Z)
• Coherent Soft Imitation Learning [17.345411907902932]
  Imitation learning methods seek to learn from an expert either through behavioral cloning (BC) of the policy or inverse reinforcement learning (IRL) of the reward. This work derives an imitation method that captures the strengths of both BC and IRL.
  arXiv  Detail & Related papers  (2023-05-25T21:54:22Z)
• Curriculum Offline Imitation Learning [72.1015201041391]
  offline reinforcement learning tasks require the agent to learn from a pre-collected dataset with no further interactions with the environment. We propose textitCurriculum Offline Learning (COIL), which utilizes an experience picking strategy for imitating from adaptive neighboring policies with a higher return. On continuous control benchmarks, we compare COIL against both imitation-based and RL-based methods, showing that it not only avoids just learning a mediocre behavior on mixed datasets but is also even competitive with state-of-the-art offline RL methods.
  arXiv  Detail & Related papers  (2021-11-03T08:02:48Z)
• DDPG++: Striving for Simplicity in Continuous-control Off-Policy Reinforcement Learning [95.60782037764928]
  We show that simple Deterministic Policy Gradient works remarkably well as long as the overestimation bias is controlled. Second, we pinpoint training instabilities, typical of off-policy algorithms, to the greedy policy update step. Third, we show that ideas in the propensity estimation literature can be used to importance-sample transitions from replay buffer and update policy to prevent deterioration of performance.
  arXiv  Detail & Related papers  (2020-06-26T20:21:12Z)
• Strictly Batch Imitation Learning by Energy-based Distribution Matching [104.33286163090179]
  Consider learning a policy purely on the basis of demonstrated behavior -- that is, with no access to reinforcement signals, no knowledge of transition dynamics, and no further interaction with the environment. One solution is simply to retrofit existing algorithms for apprenticeship learning to work in the offline setting. But such an approach leans heavily on off-policy evaluation or offline model estimation, and can be indirect and inefficient. We argue that a good solution should be able to explicitly parameterize a policy, implicitly learn from rollout dynamics, and operate in an entirely offline fashion.
  arXiv  Detail & Related papers  (2020-06-25T03:27:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.