SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models

• URL: http://arxiv.org/abs/2511.15605v1
• Date: Wed, 19 Nov 2025 16:52:23 GMT
• Title: SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models
• Abstract summary: Vision-Language-Action (VLA) models excel in robotic manipulation but are constrained by their heavy reliance on expert demonstrations.<n>Current VLA-RL methods, including group-based optimization approaches, are crippled by severe reward sparsity.<n>We propose Self-Referential Policy Optimization (SRPO), a novel VLA-RL framework.
• Score: 42.89413870143421
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-Language-Action (VLA) models excel in robotic manipulation but are constrained by their heavy reliance on expert demonstrations, leading to demonstration bias and limiting performance. Reinforcement learning (RL) is a vital post-training strategy to overcome these limits, yet current VLA-RL methods, including group-based optimization approaches, are crippled by severe reward sparsity. Relying on binary success indicators wastes valuable information in failed trajectories, resulting in low training efficiency. To solve this, we propose Self-Referential Policy Optimization (SRPO), a novel VLA-RL framework. SRPO eliminates the need for external demonstrations or manual reward engineering by leveraging the model's own successful trajectories, generated within the current training batch, as a self-reference. This allows us to assign a progress-wise reward to failed attempts. A core innovation is the use of latent world representations to measure behavioral progress robustly. Instead of relying on raw pixels or requiring domain-specific fine-tuning, we utilize the compressed, transferable encodings from a world model's latent space. These representations naturally capture progress patterns across environments, enabling accurate, generalized trajectory comparison. Empirical evaluations on the LIBERO benchmark demonstrate SRPO's efficiency and effectiveness. Starting from a supervised baseline with 48.9% success, SRPO achieves a new state-of-the-art success rate of 99.2% in just 200 RL steps, representing a 103% relative improvement without any extra supervision. Furthermore, SRPO shows substantial robustness, achieving a 167% performance improvement on the LIBERO-Plus benchmark.

Related papers

• SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning [36.32246019820315]
  Self-reflection is a powerful mechanism for credit assignment in human learning.<n>We propose Self-Reflective Policy Optimization (SRPO), a framework that internalizes this capability.<n>We demonstrate that SRPO achieves state-of-the-art performance across mathematical reasoning and long-horizon agentic benchmarks.
  arXiv  Detail & Related papers  (2026-08-24T16:55:09Z)
• Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents [15.278397068400205]
  We show that reinforcement learning post-training already provides the ingredients for effective step-level scoring.<n>We derive an implicit advantage under a general Markov decision process.<n>We validate the effectiveness of the progress advantage across three different applications.
  arXiv  Detail & Related papers  (2026-06-24T17:54:08Z)
• RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models [90.39703013636868]
  RePO-VLA is a recovery-driven policy optimization framework.<n>It assigns distinct roles to success, recovery, and failure trajectories.<n>It raises adversarial success from 20% to 75% on average and up to 80% in scaled real-world trials.
  arXiv  Detail & Related papers  (2026-05-10T08:24:05Z)
• Self-Correcting VLA: Online Action Refinement via Sparse World Imagination [55.982504915794514]
  We propose Self-Correcting VLA (SC-VLA), which achieve self-improvement by intrinsically guiding action refinement through sparse imagination.<n>SC-VLA achieve state-of-the-art performance, yielding the highest task throughput with 16% fewer steps and a 9% higher success rate than the best-performing baselines.
  arXiv  Detail & Related papers  (2026-02-25T06:58:06Z)
• TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics [46.912038830356714]
  We introduce TOPReward, a novel, probabilistically grounded temporal value function that estimates robotic task progress.<n>In zero-shot evaluations across 130+ distinct real-world tasks, TOPReward achieves 0.947 mean Value-Order Correlation (VOC) on Qwen3-VL.<n>We demonstrate that TOPReward serves as a versatile tool for downstream applications, including success detection and reward-aligned behavior cloning.
  arXiv  Detail & Related papers  (2026-02-22T19:25:48Z)
• AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering [52.67783579040657]
  AceGRPO is a machine learning system that prioritizes tasks at the agent's learning frontier to maximize learning efficiency.<n>Our trained Ace-30B model achieves a 100% valid submission rate on MLE-Bench-Lite, approaches the performance of proprietary frontier models, and outperforms larger open-source baselines.
  arXiv  Detail & Related papers  (2026-02-08T10:55:03Z)
• Verified Critical Step Optimization for LLM Agents [67.05296684575445]
  Critical Step Optimization focuses preference learning on verified critical steps.<n>Method starts from failed policy trajectories rather than expert demonstrations.<n>Experiments on GAIA-Text-103 and XBench-DeepSearch show that CSO achieves 37% and 26% relative improvement over the SFT baseline.
  arXiv  Detail & Related papers  (2026-02-03T11:41:02Z)
• Human-in-the-loop Online Rejection Sampling for Robotic Manipulation [55.99788088622936]
  Hi-ORS stabilizes value estimation by filtering out negatively rewarded samples during online fine-tuning.<n>Hi-ORS fine-tunes a pi-base policy to master contact-rich manipulation in just 1.5 hours of real-world training.
  arXiv  Detail & Related papers  (2025-10-30T11:53:08Z)
• Self-Improving Vision-Language-Action Models with Data Generation via Residual RL [29.682761652941963]
  Probe, Learn, Distill (PLD) is a three-stage plug-and-play framework that improves vision-language-action models.<n>PLD achieves near-saturated 99% task success on LIBERO, over 50% gains in SimplerEnv, and 100% success on real-world Franka and YAM arm manipulation tasks.
  arXiv  Detail & Related papers  (2025-10-30T06:24:04Z)
• Agentic Reinforcement Learning with Implicit Step Rewards [92.26560379363492]
  Large language models (LLMs) are increasingly developed as autonomous agents using reinforcement learning (agentic RL)<n>We introduce implicit step rewards for agentic RL (iStar), a general credit-assignment strategy that integrates seamlessly with standard RL algorithms.<n>We evaluate our method on three challenging agent benchmarks, including WebShop and VisualSokoban, as well as open-ended social interactions with unverifiable rewards in SOTOPIA.
  arXiv  Detail & Related papers  (2025-09-23T16:15:42Z)
• TGRPO :Fine-tuning Vision-Language-Action Model via Trajectory-wise Group Relative Policy Optimization [12.061547251822326]
  Trajectory-based Group Relative Policy Optimization (TGRPO) is an online RL-based training framework for Visual-Language-Action (VLA) models.<n>We show that TGRPO achieves an average success rate of 80.7%, which is 4.2% higher than that of Supervised Fine-Tuning (SFT) and outperforms other representative RL-based post-training methods.
  arXiv  Detail & Related papers  (2025-06-10T04:27:49Z)
• REBEL: Reinforcement Learning via Regressing Relative Rewards [59.68420022466047]
  We propose REBEL, a minimalist RL algorithm for the era of generative models.<n>In theory, we prove that fundamental RL algorithms like Natural Policy Gradient can be seen as variants of REBEL.<n>We find that REBEL provides a unified approach to language modeling and image generation with stronger or similar performance as PPO and DPO.
  arXiv  Detail & Related papers  (2024-04-25T17:20:45Z)

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.