Policy Optimization for Chain
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
HMPO: Hybrid Median-length Policy Optimization for Chain-of-Thought Compression
arXiv:2606.01934v1 Announce Type: new Abstract: Large language models achieve remarkable performance via extended chain-of-thought (CoT) reasoning, yet this lengthy process incurs substantial inference overhead. Existing CoT compression methods struggle with inflexible manual length budgets, computationally expensive multi-stage training pipelines, and fragile scalability restricted to small models. We propose HMPO (Hybrid Median-length Policy Optimization), a cost-effective, single-stage...
Taiji: Pareto Optimal Policy Optimization with Semantics-IDs Trade-off for Industrial LLM-Enhanced Recommendation
arXiv:2606.03866v1 Announce Type: new Abstract: Scaling recommender systems via large language models (LLMs) has become a prominent trend in the industry. However, aligning the LLM's semantic space with the recommender's ID space via post-training (e.g., SFT and RL) remains challenging. Existing LLM4Rec paradigms are bottlenecked by two main issues: (1) the difficulty of measuring and improving chain-of-thought (CoT) quality in open-domain recommendation during SFT, and (2) the neglect of...
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...
TARPO: Token-Wise Latent-Explicit Reasoning via Action-Routing Policy Optimization
Announce Type: new Abstract: Latent reasoning has emerged as a promising alternative to discrete Chain-of-Thought (CoT) in large language models (LLMs), enabling more expressive reasoning by operating over continuous representations. However, the inherently deterministic nature of continuous representations limits policy exploration in reinforcement learning (RL). To address this, we propose TARPO (Token-Wise Latent-Explicit Reasoning via Action-Routing Policy Optimization), a pure RL...
Guidance Contrastive Token Credit Assignment for Discrete Policy Optimization
arXiv:2605.29198v2 Announce Type: replace Abstract: Group-advantage-based reinforcement learning methods, such as GRPO and DAPO, have demonstrated strong performance across diverse domains, including mathematical reasoning and text-to-image generation. However, their reliance on sample-level rewards introduces a key limitation as uniform credit assignment across all tokens fails to capture fine-grained, token-level contributions. To address this issue, we propose Guidance Contrastive Policy...
IAPO: Information-Aware Policy Optimization for Token-Efficient Reasoning
arXiv:2602.19049v2 Announce Type: replace Abstract: Large language models increasingly rely on long chains of thought to improve accuracy, yet such gains come with substantial inference-time costs. We revisit token-efficient post-training and argue that existing sequence-level reward-shaping methods offer limited control over how reasoning effort is allocated across tokens. To bridge the gap, we propose IAPO, an information-theoretic post-training framework that assigns token-wise advantages...
Integrating Deep Learning Demand Forecasting with Multi-Objective Optimization for Circular Coffee Supply Chains: A Data-Driven Framework for Cost, Emissions, and Freshness Management
new Abstract: The coffee supply chain is one of the most complex agri-food networks, marked by geographically dispersed production, multi-tier coordination, and high sensitivity to quality and freshness. While sustainability and digitalization have gained attention, demand forecasting, optimization, and traceability are often treated separately. This study presents a two-phase integrated framework.
FGRPO: Federated GRPO with Adaptive Aggregation on Non-IID Data
Announce Type: new Abstract: Recent advances in language models have established reinforcement learning as the primary paradigm for eliciting self-correction and long-chain reasoning. While group relative policy optimization (GRPO) offers superior scalability by eliminating the critic network, deploying it on a central infrastructure entails collecting a large volume of data from distributed owners, which poses significant privacy risks. To address these concerns, we introduce federated GRPO...
Self-Evolving Scientific Agent Discovers Generalizable Physically-Reasoned Fluid Control
Announce Type: cross Abstract: While data-intensive deep reinforcement learning can optimize complex control policies, scientific discovery in physical systems fundamentally requires an interpretable chain of reasoning that connects physical evidence to structured control architectures. Here, we present a self-evolving scientific-agent workflow, driven by large language models and iterative code generation, that automates controller construction while preserving strict interpretability and...
Self-Evolving Scientific Agent Discovers Generalizable Physically-Reasoned Fluid Control
Announce Type: new Abstract: While data-intensive deep reinforcement learning can optimize complex control policies, scientific discovery in physical systems fundamentally requires an interpretable chain of reasoning that connects physical evidence to structured control architectures. Here, we present a self-evolving scientific-agent workflow, driven by large language models and iterative code generation, that automates controller construction while preserving strict interpretability and...