Self-Orchestrating Language Models: Leveraging Semantic Dependence for Efficient Inference
cs.AI, cs.CL
Submitted: 2026-09-13
Updated: 2026-09-13
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- APAR: LLMs Can Do Auto-Parallel Auto-Regressive Decoding
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Simple and Effective Masked Diffusion Language Models
- Dream 7B: Diffusion Large Language Models
- Mixtral of Experts
- LLaMA: Open and Efficient Foundation Language Models
- OpenAI o1 System Card
- Efficiently Scaling Transformer Inference
- Gemini: A Family of Highly Capable Multimodal Models
- Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators
- Accelerating LLM Inference with Staged Speculative Decoding
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- SGLang: Efficient Execution of Structured Language Model Programs
- Gemma: Open Models Based on Gemini Research and Technology
- Scaling Laws for Neural Language Models
- Show Your Work: Scratchpads for Intermediate Computation with Language Models
- LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference
- ForesightKV: Optimizing KV Cache Eviction for Reasoning Models by Learning Long-Term Contribution
- DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
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
- 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
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection