Agora: Enhancing LLM Agent Reasoning Via Auction-Based Task Allocation
cs.AI, cs.CL
Submitted: 2026-07-10
Updated: 2026-08-30
Comments: Accepted to Findings of the Association for Computational Linguistics: EMNLP 2026. 13 pages, 5 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Mechanism Design for Large Language Models
- Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysis
- Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
- Mixtral of Experts
- FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
- Learning to Route LLMs with Confidence Tokens
- MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks
- DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
- MAS-ZERO: Designing Multi-Agent Systems with Zero Supervision
- Multi-Agent Collaboration via Evolving Orchestration
- Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models
- Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing
- QA-Calibration of Language Model Confidence Scores
- Improving Factuality and Reasoning in Language Models through Multiagent Debate
- Beyond Semantic Entropy: Boosting LLM Uncertainty Quantification with Pairwise Semantic Similarity
- AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback
- MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMs
- Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- RouteLLM: Learning to Route LLMs with Preference Data
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