Two Heads Are Better Than One: Aggregating Weaker LLMs for Better Forecasts
cs.LG
Submitted: 2026-09-27
Updated: 2026-09-27
Terminology
Sources
- Diversity is the Strength of the AI Crowd
- AIA Forecaster: Technical Report
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Robust forecast aggregation via additional queries
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Kimi K2: Open Agentic Intelligence
- DeepSeek-V3 Technical Report
- Agentic Forecasting with Structured Linguistic Beliefs
- Can Language Models Use Forecasting Strategies?
- Large Language Model Prediction Capabilities: Evidence from a Real-World Forecasting Tournament
- Algorithmic Expert Aggregation
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Bench to the Future: A Pastcasting Benchmark for Forecasting Agents
- Qwen3 Technical Report
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks