POISE trains a lightweight probe on the actor's internal states to predict expected rewards for RLVR, matching DAPO performance on math benchmarks with lower compute by avoiding extra rollouts or critic models.
SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Proximal Policy Optimization (PPO) is central to aligning Large Language Models (LLMs) in reasoning tasks with verifiable rewards. However, standard token-level PPO struggles in this setting due to the instability of temporal credit assignment over long Chain-of-Thought (CoT) horizons and the prohibitive memory cost of the value model. While critic-free alternatives like GRPO mitigate these issues, they incur significant computational overhead by requiring multiple samples for baseline estimation, severely limiting training throughput. In this paper, we introduce Sequence-Level PPO (SPPO), a scalable algorithm that harmonizes the sample efficiency of PPO with the stability of outcome-based updates. SPPO reformulates the reasoning process as a Sequence-Level Contextual Bandit problem, employing a decoupled scalar value function to derive low-variance advantage signals without multi-sampling. Extensive experiments on mathematical benchmarks demonstrate that SPPO significantly surpasses standard PPO and matches the performance of computation-heavy group-based methods, offering a resource-efficient framework for aligning reasoning LLMs.
years
2026 2verdicts
UNVERDICTED 2representative citing papers
StepPO argues that LLM agents should optimize at the step level rather than token level to better handle delayed rewards and long contexts in agentic RL.
citing papers explorer
-
Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States
POISE trains a lightweight probe on the actor's internal states to predict expected rewards for RLVR, matching DAPO performance on math benchmarks with lower compute by avoiding extra rollouts or critic models.
-
StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning
StepPO argues that LLM agents should optimize at the step level rather than token level to better handle delayed rewards and long contexts in agentic RL.