reinforcement learning

Joint optimization of STAR-RIS phase coefficients and power allocation by imitation-guided multi-agent deep reinforcement learning in SWIPT-NOMA IoT networks

A multi-level framework for capacity adjustment and flexible decision-making under data constraints in production planning and control

A five-axis taxonomy is developed from 55 studies selected through a systematic Scopus review of CA research published between 2020 and 2025 and the Data-Aware Capacity Adjustment Framework is introduced as a seven-step decision-support artifact that screens CA options.

EDA-env: A Reinforcement Learning Environment for RTL-to-GDS Design with Independent Scoring

Task generator, independent scorer, 103 qualified RTL-to-GDS task packages on ASAP7, Nangate45 and Sky130HD, the scorer regression suite (143 probes), and the recorded Kimi-k3 episodes (patches, trajectories, sealed measurements) reported in the ICCAD 2026 paper "EDA-env: A Reinforcement Learning Environment for RTL-to...

EDA-env: A Reinforcement Learning Environment for RTL-to-GDS Design with Independent Scoring

Task generator, independent scorer, 103 qualified RTL-to-GDS task packages on ASAP7, Nangate45 and Sky130HD, the scorer regression suite (143 probes), and the recorded Kimi-k3 episodes (patches, trajectories, sealed measurements) reported in the ICCAD 2026 paper "EDA-env: A Reinforcement Learning Environment for RTL-to...

MudGym

A reinforcement learning environment for MUD2.

ReLA: Representation Learning and Aggregation for Scalable Job Scheduling with Reinforcement Learning

Large-scale job scheduling is a classic problem in computing systems and industrial operations, where complex workloads, workflows, or ordered job operations must be assigned to computing nodes or machines under resource, precedence, and availability constraints. Existing solvers can provide useful reference solutions,...

MudGym

A reinforcement learning environment for MUD2.

SCPFL: A Safety Reinforcement Learning Framework for Joint Energy-Fairness Optimization in Long-term Federated Learning

Federated Learning (FL) enables heterogeneous clients to collaboratively train a shared model while keeping raw data local. In practical FL systems, client participation is often constrained by limited battery energy, and long-term unselection of clients may lower their willingness to participate, which further reduces...

Accelerating Long-Tail Generation in Synchronous RLHF Training via Adaptive Tensor Parallelism

Reinforcement Learning from Human Feedback (RLHF) has become a key post-training paradigm for improving model quality. However, the synchronous three-stage RLHF pipeline is often bottlenecked by the generation stage, where response-length skew causes the effective batch size to shrink rapidly during decoding, leaving G...

Large Language Model-Enhanced Multi-Agent Reinforcement Learning for Autonomous Enterprise Workflow Orchestration via Graph Semantic Routing

# LeMARLA **Large Language Model-Enhanced Multi-Agent Reinforcement Learning for Autonomous Enterprise Workflow Orchestration via Graph Semantic Routing.** LeMARLA couples an LLM-driven task decomposition module, a heterogeneous graph attention routing module over tasks, employees and skills, and a CTDE multi-agent rei...

Multilingual Sentiment-Aware Text Summarization: A Reinforcement Learning Approach for Consistency Maintenance

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing

This work introduces a conditional length-penalized post-training algorithm that intertwines verification accuracy with bounded reasoning length, halting collapse and recovering performance, and offers both a scalable algorithmic patch and a long-term architectural blueprint for aligning reasoning models with real-worl...