Freshness-Aware Prioritized Experience Replay for LLM/VLM Reinforcement Learning

• URL: http://arxiv.org/abs/2604.16918v1
• Date: Sat, 18 Apr 2026 08:51:29 GMT
• Title: Freshness-Aware Prioritized Experience Replay for LLM/VLM Reinforcement Learning
• Abstract summary: Reinforcement Learning (RL) has achieved impressive success in post-training Large Language Models (LLMs) and Vision-Language Models (VLMs)<n>These methods discard all collected trajectories after a single gradient update, resulting in poor sample efficiency.<n>We propose Freshness-Aware PER, which addresses this priority staleness problem by augmenting any PER-based priority with a multiplicative exponential age decay.
• Score: 43.63475878891097
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement Learning (RL) has achieved impressive success in post-training Large Language Models (LLMs) and Vision-Language Models (VLMs), with on-policy algorithms such as PPO, GRPO, and REINFORCE++ serving as the dominant paradigm. However, these methods discard all collected trajectories after a single gradient update, resulting in poor sample efficiency, particularly wasteful for agentic tasks where multi-turn environment interactions are expensive. While Experience Replay drives sample efficiency in classic RL by allowing agents to reuse past trajectories and prioritize informative ones, directly applying Prioritized Experience Replay (PER) to LLMs fails. The rapid policy evolution of billion-parameter models renders stored priorities stale, causing old high-priority trajectories to dominate sampling long after they have become uninformative. We propose Freshness-Aware PER, which addresses this priority staleness problem by augmenting any PER-based priority with a multiplicative exponential age decay grounded in effective sample size analysis. To the best of our knowledge, Freshness-Aware PER is the first work to successfully apply PER to LLM/VLM reinforcement learning. We evaluate on eight multi-step agentic, reasoning, and math competition tasks with 0.5B, 3B, and 7B models. Freshness-Aware PER significantly outperforms on-policy baselines, achieving +46% on NQ Search, +367% on Sokoban, and +133% on VLM FrozenLake, while standard PER without age decay consistently degrades performance. Our code is publicly available at https://github.com/Vision-CAIR/Freshness-Aware-PER.

Related papers

• Off-Policy Value-Based Reinforcement Learning for Large Language Models [25.962820072445222]
  ReVal is a Bellman-update-based method that combines stepwise signals capturing internal consistency with trajectory-level signals derived from outcome verification.<n>On DeepSeek-R1-Distill-1.5B, ReVal improves training efficiency and achieves improvement of 2.7% in AIME24 and 4.5% in out-of-domain benchmark GPQA over GRPO.
  arXiv  Detail & Related papers  (2026-03-24T15:55:02Z)
• VLM-Guided Experience Replay [41.08659748023147]
  We propose to use Vision-Language Models (VLMs) to guide the prioritization of experiences in the replay buffer.<n>Our key idea is to use a frozen, pre-trained VLM as an automated evaluator to identify and prioritize promising sub-trajectories from the agent's experiences.<n>Across scenarios, including game-playing and robotics, agents trained with our proposed prioritization method achieve 11-52% higher average success rates and improve sample efficiency by 19-45% compared to previous approaches.
  arXiv  Detail & Related papers  (2026-02-02T10:19:59Z)
• Tailored Primitive Initialization is the Secret Key to Reinforcement Learning [61.29280885291581]
  Reinforcement learning (RL) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs)<n>We argue that initializing LLMs with diverse, high-quality reasoning primitives is essential for achieving stable and sample-efficient RL training.<n>We propose Tailor, a finetuning pipeline that automatically discovers and curates novel reasoning primitives.
  arXiv  Detail & Related papers  (2025-11-16T03:12:40Z)
• ActiveVLN: Towards Active Exploration via Multi-Turn RL in Vision-and-Language Navigation [57.399685080574756]
  Existing MLLM-based VLN methods rely on imitation learning (IL) and often use DAgger for post-training.<n>We propose ActiveVLN, a VLN framework that explicitly enables active exploration through multi-turn RL.<n>Experiments show that ActiveVLN achieves the largest performance gains over IL baselines compared to both DAgger-based and prior RL-based post-training methods.
  arXiv  Detail & Related papers  (2025-09-16T03:31:46Z)
• An Early FIRST Reproduction and Improvements to Single-Token Decoding for Fast Listwise Reranking [50.81324768683995]
  FIRST is a novel approach that integrates a learning-to-rank objective and leveraging the logits of only the first generated token. We extend the evaluation of FIRST to the TREC Deep Learning datasets (DL19-22), validating its robustness across diverse domains. Our experiments confirm that fast reranking with single-token logits does not compromise out-of-domain reranking quality.
  arXiv  Detail & Related papers  (2024-11-08T12:08:17Z)
• VinePPO: Refining Credit Assignment in RL Training of LLMs [66.80143024475635]
  We propose VinePPO, a straightforward approach that leverages the flexibility of language environments to compute unbiased Monte Carlo-based estimates.<n>Our method consistently outperforms PPO and other baselines across MATH and GSM8K datasets in less wall-clock time.
  arXiv  Detail & Related papers  (2024-10-02T15:49:30Z)
• How Can LLM Guide RL? A Value-Based Approach [68.55316627400683]
  Reinforcement learning (RL) has become the de facto standard practice for sequential decision-making problems by improving future acting policies with feedback. Recent developments in large language models (LLMs) have showcased impressive capabilities in language understanding and generation, yet they fall short in exploration and self-improvement capabilities. We develop an algorithm named LINVIT that incorporates LLM guidance as a regularization factor in value-based RL, leading to significant reductions in the amount of data needed for learning.
  arXiv  Detail & Related papers  (2024-02-25T20:07:13Z)
• MAC-PO: Multi-Agent Experience Replay via Collective Priority Optimization [12.473095790918347]
  We propose name, which formulates optimal prioritized experience replay for multi-agent problems. By minimizing the resulting policy regret, we can narrow the gap between the current policy and a nominal optimal policy.
  arXiv  Detail & Related papers  (2023-02-21T03:11:21Z)

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.