From RL Papers to Framework Code: Inclusion and Review in Seven Open-Source Training Frameworks
Paper • 2610.28027 • Published • 13
Ayaka Nishimura
ayakani
·
AI & ML interests
anomaly detection
multi-agent RL
reward hacking
Recent Activity
upvoted a paper about 7 hours ago
From RL Papers to Framework Code: Inclusion and Review in Seven Open-Source Training Frameworks upvoted a paper about 7 hours ago
Language Models Learn to Improve Language Models upvoted a paper about 7 hours ago
AgenticRoboRL: Bringing Coding-Agent Post-Training to Agentic RoboticsOrganizations
None yet
upvoted 7
papers about 7 hours ago
Language Models Learn to Improve Language Models
Paper • 2610.23344 • Published • 7
AgenticRoboRL: Bringing Coding-Agent Post-Training to Agentic Robotics
Paper • 2610.28589 • Published • 37
Harness Scaling for Generalizable Agentic Reinforcement Learning
Paper • 2610.29458 • Published • 22
PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis
Paper • 2610.20538 • Published • 60
Answering in the User's Variety: Calibrated Accommodation Pairs for Post-Training
Paper • 2610.28474 • Published • 13
Toward Part-Aware Choral Transcription with singing voice assignment
Paper • 2610.09861 • Published • 13
upvoted 4
papers 1 day ago
Self-Evolving Coding Agents via Harness-Policy Optimization
Paper • 2610.22791 • Published • 56
CoworkEnv: Synthesizing Training Environments for Long-Horizon Cowork Agents
Paper • 2610.24960 • Published • 52
Think Visually Across Space and Time: Grounded Reasoning for Video Segmentation
Paper • 2610.25090 • Published • 24
Interlock: From Local Correctness to Task Completion in Long-Horizon Agents
Paper • 2610.19686 • Published • 49
upvoted 6
papers 2 days ago
AVC-Reward: Event-Centric Audio-Video Consistency Evaluation
Paper • 2610.22321 • Published • 17
Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries
Paper • 2610.22273 • Published • 10
Lean4AgenticRL: Advancing Agentic RL with Verifiable Multi-level Process Rewards
Paper • 2610.22448 • Published • 24
Learning to Think and Explore in 3D World
Paper • 2610.21783 • Published • 140
FC-SWE: Failure-Conditioned RL for Long-Horizon Software Engineering Agents
Paper • 2610.07898 • Published • 9
Tree-Aware Posterior Distillation for Long-Horizon Agentic Reinforcement Learning
Paper • 2610.23181 • Published • 54
upvoted 3
papers 3 days ago
Beyond Policy Rollouts: Embedding-Space Directional Exploration with Anchored Noise for LLM RLVR
Paper • 2610.16105 • Published • 16
OmniVerifier-C1: Decomposed Graded Verifier for Rule-Governed Generative World Modeling
Paper • 2610.22355 • Published • 44
Cowork-Gym: Synthesizing Interactive Work Environments at Scale
Paper • 2610.17670 • Published • 13