All news

11 articles

Min score

Reset

blogHugging Face Blog·23 Oct 20264.9
Turning Database Grading into RL Rewards: Post-Training Agents with ThinkingBox
ThinkingBox turns database end-state checks into RL rewards for post-training agents, with training code released.
llm-agents llm-evaluation Reinforcement Learning
paperarXiv (systems, data, ML)·22 Oct 20264.0
Same Luck, Different Choice: Twin-World Credit Assignment for Agentic Reinforcement Learning
Twin-world counterfactual credit assignment for agentic RL.
llm-agents Reinforcement Learning
blogSebastian Raschka·24 Oct 20263.8
Building Reasoning Models from the Ground Up: A Full Video Course
A full video course on building reasoning LLMs from scratch, covering inference-time scaling and RL training.
Reinforcement Learning llm-reasoning llm-training
paperHugging Face Daily Papers·20 Oct 20263.6
From RL Papers to Framework Code: Inclusion and Review in Seven Open-Source Training Frameworks
How RL papers get into seven open-source LLM training frameworks.
Reinforcement Learning llm-training
paperarXiv (systems, data, ML)·23 Oct 20263.6
Questioning Instrumental Convergence in RLVR: Checkpoint Evidence from OLMo-3
OLMo-3 checkpoints show little evidence of instrumental convergence in RLVR.
Reinforcement Learning llm-safety
paperGoogle Scholar·25 Oct 20263.5
ReflectPO: Reflection-Guided Policy Optimization for Long-Horizon LLM Agents
ReflectPO uses the agent reflections to guide policy optimization for long-horizon tool-using LLM agents.
llm-agents Reinforcement Learning
paperIEEE Xplore·1 Nov 20263.4
Overselling-Aware Task Scheduling in MEC With Deep Reinforcement Learning
Deep reinforcement learning task scheduling for mobile edge computing that accounts for providers overselling capacity.
edge-computing Reinforcement Learning resource-scheduling
paperIEEE Xplore·1 Nov 20263.4
Curiosity-Driven Collaborative Request Scheduling in Mobile Edge-Cloud Systems
Uses curiosity-driven reinforcement learning to schedule requests collaboratively across mobile edge and cloud servers.
edge-computing Reinforcement Learning resource-scheduling
paperIEEE Xplore·1 Nov 20263.2
Improving Policy Learning via Language-Guided State Representation in World Models
Language-guided state representations improve policy learning in world models.
Reinforcement Learning world-models
paperarXiv (systems, data, ML)·23 Oct 20263.1
METTA: Memory-Enhanced Test-Time Adaptation for Meta-Reinforcement Learning
Memory-enhanced test-time adaptation for meta-RL.
Reinforcement Learning
paperIEEE Xplore·1 Nov 20263.1
Continual DRL on Dynamic Graphs for UAV-Assisted Multi-User 360 VR Video Streaming
Continual deep RL on dynamic graphs for UAV-assisted multi-user 360 VR video streaming.
Reinforcement Learning video-streaming 360-video