Debate as Reward: A Multi-Agent Reward System for Scientific Ideation via RL Post-Training
cs.AI, cs.LG
Submitted: 2026-04-17
Updated: 2026-11-14
Terminology
Sources
- IdeaBench: Benchmarking Large Language Models for Research Idea Generation
- SCI-IDEA: Context-Aware Scientific Ideation Using Token and Sentence Embeddings
- LDC: Learning to Generate Research Idea with Dynamic Control
- Understanding R1-Zero-Like Training: A Critical Perspective
- The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
- Improving LLM-Generated Code Quality with GRPO
- Proximal Policy Optimization Algorithms
- Large Language Models for Scientific Idea Generation: A Creativity-Centered Survey
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers
- Defining and Characterizing Reward Hacking
- SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models
- GeometryZero: Advancing Geometry Solving via Group Contrastive Policy Optimization
- The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
- Self-Rewarding Language Models
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents