When LLMs Develop Languages: Symbolic Communication for Efficient Multi-Agent Reasoning
cs.AI, cs.NE
Submitted: 2026-06-28
Updated: 2026-10-10
Code: https://github.com/pzqpzq/LSF_MDia
Terminology
Sources
- Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching
- Intermediate Languages Matter: Formal Choice Drives Neurosymbolic LLM Reasoning
- Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models
- Compressed Chain of Thought: Efficient Reasoning Through Dense Representations
- Training Verifiers to Solve Math Word Problems
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Measuring Mathematical Problem Solving With the MATH Dataset
- Emergent Multi-Agent Communication in the Deep Learning Era
- Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost
- Neuronal Group Communication for Efficient Neural representation
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
- ORION: Teaching Language Models to Reason Efficiently in the Language of Thought
- R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search
- Chain of Draft: Thinking Faster by Writing Less
- Qwen3 Technical Report
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