Shared Item-Level Error Limits the Aggregation of Small Language Models in Fermi Estimation
cs.MA, cs.AI
Submitted: 2026-11-12
Updated: 2026-11-12
Code: https://github.com/landy8697/open-scioly-fermi
Terminology
Sources
- Number Representations in LLMs: A Computational Parallel to Human Perception
- Weber's Law in Transformer Magnitude Representations: Efficient Coding, Representational Geometry, and Psychophysical Laws in Language Models
- ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs
- Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?
- Improving Factuality and Reasoning in Language Models through Multiagent Debate
- LLMs are Overconfident: Evaluating Confidence Interval Calibration with FermiEval
- Great Models Think Alike and this Undermines AI Oversight
- How Much Coffee Was Consumed During EMNLP 2019? Fermi Problems: A New Reasoning Challenge for AI
- More Agents Is All You Need
- LLM for Complex Reasoning Task: An Exploratory Study in Fermi Problems
- Representational Collapse in Multi-Agent LLM Committees: Measurement and Diversity-Aware Consensus
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity
Related papers
- MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents
- Iterative Negotiation and Oversight: A Case Study in Decentralized Air Traffic Management
- Towards using Large Language Models for Risk Negotiation and Consensus-building in One Health contexts
- A-MapReduce: Executing Wide Search via Agentic MapReduce
- AgentCue: Statistical Summaries for Guiding Decentralized Multi-Agent Self-Organization
- Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning