A Communication-Theoretic Framework for LLM Agents: Cost-Aware Adaptive Reliability
cs.LG, cs.AI, cs.CL, cs.IT, math.IT
Submitted: 2026-05-09
Updated: 2026-11-07
Terminology
Sources
- Harnessing Multiple Large Language Models: A Survey on LLM Ensemble
- Training Verifiers to Solve Math Word Problems
- Certified Self-Consistency: Statistical Guarantees and Test-Time Training for Reliable Reasoning in LLMs
- Language Models (Mostly) Know What They Know
- Scaling Laws for Neural Language Models
- Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?
- GPT-4 Technical Report
- Test-Time Scaling Makes Overtraining Compute-Optimal
- Can You Trust LLM Judgments? Reliability of LLM-as-a-Judge
- Don't Always Pick the Highest-Performing Model: An Information Theoretic View of LLM Ensemble Selection
- Attention-MoA: Enhancing Mixture-of-Agents via Inter-Agent Semantic Attention and Deep Residual Synthesis
- Scaling Test-time Compute for LLM Agents
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning