Home Knowledge Base Group Relative Policy Optimization

Group Relative Policy Optimization

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

MDP-GRPO: Stabilized Group Relative Policy Optimization for Multi-Constraint Instruction Following

arXiv:2606.06058v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards is ideal for multi-constraint instruction following, yet standard group-relative policy optimization (GRPO) becomes unstable under discrete, low-dispersion rewards, where within-group reward distributions are frequently homogeneous. We identify and formalize three pathologies of z-score group normalization in this regime: low-variance amplification, mean-centering blindness, and zero-variance...

arXiv CS 5d ago

BiasGRPO: Stabilizing Bias Mitigation in High-Variance Reward Landscapes via Group-Relative Policy Optimization

arXiv:2606.04807v1 Announce Type: new Abstract: Mitigating social bias in Large Language Models (LLMs) presents a distinct alignment challenge: unlike verifiable tasks, bias lacks a single ground truth, creating a high-variance, subjective reward landscape. Previous preference-based fine-tuning methods have major trade-offs: Direct Preference Optimization (DPO) is limited by the lack of exploration inherent in offline training, while Proximal Policy Optimization (PPO) can lead to training...

arXiv CS 6d ago

Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation

arXiv:2605.21125v2 Announce Type: replace Abstract: Group Relative Policy Optimization (GRPO), a prominent algorithm within the Reinforcement Learning from Verifiable Rewards (RLVR) framework, has achieved strong results in improving the reasoning capabilities of large language models (LLMs). However, GRPO is prone to advantage collapse, a failure mode where homogeneous rewards within a group (e.g., all correct or all incorrect answers) yield near-zero advantages and vanishing gradients. To...

arXiv CS 8d ago

Can the Environment Speak for Itself? $T^{2}$-GRPO: A Turn-Trajectory Group Relative Policy Optimization for Caregiver Agents

arXiv:2606.08875v1 Announce Type: new Abstract: Optimizing large language models (LLMs) for long-horizon caregiver agents requires balancing delayed task objectives with immediate environment dynamics, such as patient distress and resistance. In dementia care, this balance is especially difficult: trajectory level rewards are too sparse for turn level credit assignment, while external LLM-based evaluators are costly and can misread fragmented or indirect patient responses. To address this...

arXiv CS 1d ago

B-GRTO: Bootstrapped Group Relative Tool Optimization for Referring Segmentation

Announce Type: replace Abstract: Segmentation is a fundamental task in computer vision, underpinning pixel-level scene understanding and serving as a cornerstone for applications ranging from autonomous perception to medical image analysis. For complex referring segmentation, recent methods pair large vision-language models with segmentation decoders: the former analyzes the image and prompt, while the latter predicts the target mask. Although reinforcement learning improves...

arXiv CS 8d ago

SALT: When More Rollouts Don't Help in Group-Based Policy Optimization and How to Make Them Matter

Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) often adopts GRPO-style group-relative updates, sampling multiple rollouts per prompt to construct normalized learning signals. However, merely increasing the number of rollouts does not reliably strengthen learning: under GRPO-style group normalization, per-rollout policy-gradient features can concentrate into a low-rank, signed geometry, causing substantial cancellation during aggregation and weakening the...

arXiv CS 5d ago

Soft Sequence Policy Optimization

arXiv:2602.19327v3 Announce Type: replace Abstract: A significant portion of recent research on Large Language Model (LLM) alignment focuses on developing new policy optimization methods based on Group Relative Policy Optimization (GRPO). Two prominent directions have emerged: (i) a shift toward sequence-level importance sampling weights that better align with the sequence-level rewards used in many tasks, and (ii) alternatives to the PPO-style clipping that aim to avoid the associated loss...

arXiv CS 5d ago

Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization

arXiv:2605.15980v2 Announce Type: replace Abstract: Group Relative Policy Optimization has emerged as essential for aligning video diffusion models with human preferences, but faces a critical computational bottleneck: training a 14B parametered model typically demands hundreds of GPU days per experiment. Existing efficiency methods reduce costs through sliding window subsampling training timesteps, but fundamentally compromise optimization, exhibiting severe instability and failing to reach...

arXiv CS 6d ago

Safe Equilibrium Policy Optimization for Strategic Agent Policies

arXiv:2605.30854v1 Announce Type: new Abstract: Language models fine-tuned with reinforcement learning typically optimize for task reward, ignoring multi-agent strategic structure. Because these agents condition on natural language game-state descriptions and emit actions through free-form generation, strategic failure modes -- exploiting weaker opponents, coordinating on harmful equilibria, and externalizing costs are inseparable from the language interface itself. We propose Safe...

arXiv CS 9d ago

Momentum for Reasoning: Dense Intrinsic Signals in Policy Optimization

Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for eliciting long-chain reasoning in large language models. However, existing methods based on Group Relative Policy Optimization (GRPO) rely on a binary outcome reward, which induces two structural failure modes: Zero-Advantage Collapse, in which all rollouts in a group share the same outcome and the gradient vanishes, and Hallucinated Certainty, in which the model becomes...

arXiv CS 1d ago