Research map / Large language models / Agents, code and math
Decision Aggregation under Quantal Response
Zhihuan Huang, Yichong Xia, Yuqing Kong
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use moderately stochastic experts instead of perfectly rational ones in a team with optimal combination | team of quantal-response experts · Illustrative buy/sell example | average utility: 0.5 -> 0.51 | Improved |
| raise LLM temperature from 0 for a single expert (n=1) (ablation) | gpt-4o-mini · Bayesian box-ball and MathQA | utility / accuracy | Hurt |
| raise LLM temperature above 0 with majority/plurality voting over n=3 or 5 (ablation) | gpt-4o-mini · Bayesian box-ball and MathQA | utility / accuracy | Improved |
| increase number of experts n from 1 to 3 and 5 (ablation) | majority/plurality voting · Bayesian box-ball and MathQA | utility / accuracy | Improved |
| raise temperature from 0 to 0.5 and 1.0 (ablation) | gpt-4o-mini quantal response · Bayesian box-ball task | fitted lambda: 13.25 at t=0.5 -> 8.93 at t=1.0 | Hurt |
Closest papers by meaning
- Systematic Failures in Collective Reasoning under Distributed Information in Multi-Agent LLMs (ICML 2026 · similarity 0.86)
- Modeling Boundedly Rational Agents with Latent Inference Budgets (ICLR 2024 · similarity 0.86)
- Policy Aggregation (NeurIPS 2024 · similarity 0.86)
- Aggregating Quantitative Relative Judgments: From Social Choice to Ranking Prediction (NeurIPS 2024 · similarity 0.85)
- Weak Strategyproofness in Randomized Social Choice (AAAI 2025 · similarity 0.85)
- Emergence of Biased Consensus in Multi-Agent LLM Debates (ICML 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
