RankBuffer: Efficient Ranking-Based Rewards for Open-Ended Generation

cs.AI

Submitted: 2026-09-29

Updated: 2026-09-29

Code: https://github.com/PuffYang/RankBuffer

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Constitutional AI: Harmlessness from AI Feedback
• EvoRubrics: Dynamic Rubrics as Rewards via Adversarial Co-Evolution for LLM Reinforcement Learning
• Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Reinforcement Learning with Rubric Anchors
• Open Rubric System: Scaling Reinforcement Learning with Pairwise Adaptive Rubric
• From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline
• E2Rank: Unifying Text Embedding and Listwise Reranking for Effective and Efficient Search
• GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
• Understanding R1-Zero-Like Training: A Critical Perspective
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Rethinking Rubric Generation for Improving LLM Judge and Reward Modeling for Open-ended Tasks
• RRC: Unlocking Generative Reward Models in LLM Reinforcement Learning via Ranking-Based Reward Construction
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training
• Qwen3 Technical Report
• Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge
• Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation
• OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search
• ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems