AdaCuRL: Adaptive Curriculum Reinforcement Learning with Invalid Sample Mitigation and Historical Revisiting

• URL: http://arxiv.org/abs/2511.09478v1
• Date: Thu, 13 Nov 2025 01:57:04 GMT
• Title: AdaCuRL: Adaptive Curriculum Reinforcement Learning with Invalid Sample Mitigation and Historical Revisiting
• Abstract summary: Reinforcement learning can enhance reasoning in large language models (LLMs)<n>Existing methods suffer from Gradient Starvation and Policy Degradation when training directly on samples with mixed difficulty.<n>AdaCuRL integrates coarse-to-fine difficulty estimation with adaptive curriculum scheduling.
• Score: 23.630999806649914
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning (RL) has demonstrated considerable potential for enhancing reasoning in large language models (LLMs). However, existing methods suffer from Gradient Starvation and Policy Degradation when training directly on samples with mixed difficulty. To mitigate this, prior approaches leverage Chain-of-Thought (CoT) data, but the construction of high-quality CoT annotations remains labor-intensive. Alternatively, curriculum learning strategies have been explored but frequently encounter challenges, such as difficulty mismatch, reliance on manual curriculum design, and catastrophic forgetting. To address these issues, we propose AdaCuRL, a Adaptive Curriculum Reinforcement Learning framework that integrates coarse-to-fine difficulty estimation with adaptive curriculum scheduling. This approach dynamically aligns data difficulty with model capability and incorporates a data revisitation mechanism to mitigate catastrophic forgetting. Furthermore, AdaCuRL employs adaptive reference and sparse KL strategies to prevent Policy Degradation. Extensive experiments across diverse reasoning benchmarks demonstrate that AdaCuRL consistently achieves significant performance improvements on both LLMs and MLLMs.

Related papers

• Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards [73.44333771806282]
  Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective paradigm for improving the reasoning capabilities of large language models.<n>We propose Correction-Oriented Policy Optimization (CIPO), a simple and effective extension to RLVR that converts on-policy failed trajectories into correction-oriented supervision.<n>CIPO improves learning effectiveness while explicitly enhancing the model's ability to correct its own errors.
  arXiv  Detail & Related papers  (2026-05-14T08:22:21Z)
• Towards Sample-Efficient and Stable Reinforcement Learning for LLM-based Recommendation [56.92367609590823]
  Long Chain-of-Thought (Long CoT) reasoning has shown promise in Large Language Models (LLMs)<n>We argue that Long CoT is inherently ill-suited for the sequential recommendation domain.<n>We propose RISER, a novel Reinforced Item Space Exploration framework for Recommendation.
  arXiv  Detail & Related papers  (2026-01-31T10:02:43Z)
• CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs [53.749193998004166]
  Curriculum learning plays a crucial role in enhancing the training efficiency of large language models.<n>We propose CurES, an efficient training method that accelerates convergence and employs Bayesian posterior estimation to minimize computational overhead.
  arXiv  Detail & Related papers  (2025-10-01T15:41:27Z)
• Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning [77.92320830700797]
  Reinforcement Learning has played a central role in enabling reasoning capabilities of Large Language Models.<n>We propose a tractable computational framework that tracks and leverages curvature information during policy updates.<n>The algorithm, Curvature-Aware Policy Optimization (CAPO), identifies samples that contribute to unstable updates and masks them out.
  arXiv  Detail & Related papers  (2025-10-01T12:29:32Z)
• TACO: Think-Answer Consistency for Optimized Long-Chain Reasoning and Efficient Data Learning via Reinforcement Learning in LVLMs [50.820065021136024]
  DeepSeek R1 has significantly advanced complex reasoning for large language models (LLMs)<n>Recent methods have attempted to replicate R1's reasoning capabilities in multimodal settings.<n>We propose TACO, a novel reinforcement learning algorithm for visual reasoning.
  arXiv  Detail & Related papers  (2025-05-27T06:30:48Z)
• Curriculum-RLAIF: Curriculum Alignment with Reinforcement Learning from AI Feedback [36.919559767160415]
  This paper attempts to enhance the generalizability of reward models through a data-centric approach.<n>We propose a novel framework, $textitCurriculum-RLAIF, which constructs preference pairs with varying difficulty levels.<n>Our experimental results suggest that reward models trained with Curriculum-RLAIF achieve improved generalizability.
  arXiv  Detail & Related papers  (2025-05-26T14:53:08Z)
• Is Difficulty Calibration All We Need? Towards More Practical Membership Inference Attacks [16.064233621959538]
  We propose a query-efficient and computation-efficient MIA that directly textbfRe-levertextbfAges the original membershitextbfP scores to mtextbfItigate the errors in textbfDifficulty calibration.
  arXiv  Detail & Related papers  (2024-08-31T11:59:42Z)
• Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models [104.55763564037831]
  We train a regression model that leverages attention maps, probabilities on the current generation step, and recurrently computed uncertainty scores from previously generated tokens.<n>Our evaluation shows that the proposed method is highly effective for selective generation, achieving substantial improvements over rivaling unsupervised and supervised approaches.
  arXiv  Detail & Related papers  (2024-08-20T09:42:26Z)
• Towards Effective Evaluations and Comparisons for LLM Unlearning Methods [97.2995389188179]
  This paper seeks to refine the evaluation of machine unlearning for large language models.<n>It addresses two key challenges -- the robustness of evaluation metrics and the trade-offs between competing goals.
  arXiv  Detail & Related papers  (2024-06-13T14:41:00Z)
• Large Language Models are Miscalibrated In-Context Learners [22.30783674111999]
  In this work, we deliver an in-depth analysis of the behavior across different choices of learning methods.<n>We observe that the miscalibration problem exists across all learning methods in low-resource setups.<n>We find that self-ensembling with max probability produces robust and calibrated predictions.
  arXiv  Detail & Related papers  (2023-12-21T11:55:10Z)
• 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)
• Assessor-Guided Learning for Continual Environments [17.181933166255448]
  This paper proposes an assessor-guided learning strategy for continual learning. An assessor guides the learning process of a base learner by controlling the direction and pace of the learning process. The assessor is trained in a meta-learning manner with a meta-objective to boost the learning process of the base learner.
  arXiv  Detail & Related papers  (2023-03-21T06:45:14Z)

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.