SPO++: Stream-Aligned Policy Optimization for Asynchronous Agentic RL

• URL: http://arxiv.org/abs/2608.24870v1
• Date: Tue, 25 Aug 2026 17:52:19 GMT
• Title: SPO++: Stream-Aligned Policy Optimization for Asynchronous Agentic RL
• Abstract summary: Group-relative reinforcement learning waits for sibling rollouts of the same prompt.<n>We show that trajectory centering generally does not center the token-weighted quantity consumed by the actor.<n>We additionally organize prompt evidence by the policy event that generated it rather than learner receipt order.
• Score: 6.238212335422264
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Group-relative reinforcement learning waits for sibling rollouts of the same prompt, which is costly for long and variable tool-use trajectories. Single-stream Policy Optimization (SPO) removes this dependency with a persistent prompt-level value estimate, but its recipe whitens one advantage per trajectory before optimizing a token-mean actor loss. We show that trajectory centering generally does not center the token-weighted quantity consumed by the actor, and fix the mismatch by standardizing terminal-outcome advantages under the action-token measure. We additionally organize prompt evidence by the policy event that generated it rather than learner receipt order. Across matched runs on ALFWorld at two model scales and on Math-TIR, SPO++ improves online learning efficiency over SPO. A paired ablation identifies action-token-measure normalization as the strongest tested component.

Related papers

• Post-Training at the Edge of Detectability: A Game-Theoretic Approach to Fine-Tuning [58.088509347353465]
  Reinforcement learning (RL) fine-tuning is widely used in language model training.<n>We propose a game-theoretic framework that gives this trade-off an explicit statistical interpretation.
  arXiv  Detail & Related papers  (2026-07-29T00:19:09Z)
• Rank-Then-Act: Reward-Free Control from Frame-Order Progress [5.357451930622806]
  Rank-Then-Act (RTA) is a framework for learning control policies from expert video demonstrations without environment rewards.<n>We train a Vision-Language Model (VLM) offline as a progress-based ordinal scorer.<n>We compute the Spearman rank correlation between predicted progress rankings and true temporal indices, yielding a bounded, scale-invariant learning signal.
  arXiv  Detail & Related papers  (2026-07-02T08:50:32Z)
• TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning [52.67756371231985]
  Reinforcement learning with verifiable rewards (RLVR) is a promising approach for enhancing reasoning and agentic behavior in large language models.<n>We introduce Tree Rollout Allocation for Contrastive Exploration (TRACE), a unified rollout allocation framework.<n>Technically, TRACE allocates rollout budget to both prompt roots and intermediate prefixes that are most likely to yield mixed terminal rewards.
  arXiv  Detail & Related papers  (2026-06-09T17:16:03Z)
• Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training [50.86545293331458]
  Reinforcement learning is structurally harder than supervised learning because the policy changes the data distribution it learns from.<n>We present a simple yet effective batch-adaptive objective that replaces fixed clipping with the normalized effective sample size of the policy ratios.
  arXiv  Detail & Related papers  (2026-05-12T16:44:47Z)
• Rethinking Importance Sampling in LLM Policy Optimization: A Cumulative Token Perspective [22.848847562976633]
  Existing methods face a fundamental bias-variance dilemma: token-level IS ratios, as adopted by PPO and GRPO, introduce bias by ignoring prefix state distribution mismatch.<n>We propose CTPO, which combines the cumulative token IS ratio with position-adaptive clipping that scales log-space clip bounds according to the natural $sqrtt$ growth of the cumulative log-ratio.
  arXiv  Detail & Related papers  (2026-05-08T06:35:02Z)
• ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking [84.07076200941474]
  ArenaRL is a reinforcement learning paradigm that shifts from pointwise scalar scoring to intra-group relative ranking.<n>We construct an intra-group adversarial arena and devise a tournament-based ranking scheme to obtain stable advantage signals.<n>Experiments show that ArenaRL substantially outperforms standard RL baselines.
  arXiv  Detail & Related papers  (2026-01-10T08:43:07Z)
• ASPO: Asymmetric Importance Sampling Policy Optimization [31.38346888572171]
  The Importance Sampling (IS) ratios of positive-advantage tokens are mismatched, leading to unbalanced token weighting for positive and negative tokens.<n>This mismatch suppresses the update of low-probability tokens while over-amplifying already high-probability ones.<n>We propose Asymmetric Importance Sampling Policy Optimization (ASPO), which uses a simple yet effective strategy that flips the IS ratios of positive-advantage tokens.
  arXiv  Detail & Related papers  (2025-10-07T15:54:24Z)
• Efficient Preference-based Reinforcement Learning via Aligned Experience Estimation [37.36913210031282]
  Preference-based reinforcement learning (PbRL) has shown impressive capabilities in training agents without reward engineering. We propose SEER, an efficient PbRL method that integrates label smoothing and policy regularization techniques.
  arXiv  Detail & Related papers  (2024-05-29T01:49:20Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• You Only Need End-to-End Training for Long-Tailed Recognition [8.789819609485225]
  Cross-entropy loss tends to produce highly correlated features on imbalanced data. We propose two novel modules, Block-based Relatively Balanced Batch Sampler (B3RS) and Batch Embedded Training (BET) Experimental results on the long-tailed classification benchmarks, CIFAR-LT and ImageNet-LT, demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2021-12-11T11:44:09Z)
• Provably Efficient Algorithms for Multi-Objective Competitive RL [54.22598924633369]
  We study multi-objective reinforcement learning (RL) where an agent's reward is represented as a vector. In settings where an agent competes against opponents, its performance is measured by the distance of its average return vector to a target set. We develop statistically and computationally efficient algorithms to approach the associated target set.
  arXiv  Detail & Related papers  (2021-02-05T14:26:00Z)

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.