Skip to content

When LLMs Develop Languages: Symbolic Communication for Efficient Multi-Agent Reasoning

Jun 2026 · arXiv.org · Vol abs/2606.29354 · 5 citations · 56 references
Computer Science

Abstract

Chain-of-Thought (CoT) improves large language models (LLMs) on difficult reasoning tasks, but it often incurs long natural-language rationales that are poorly aligned with efficient machine reasoning. We propose Communicative Language Symbolism Routing (CLSR), a test-time framework in which multiple LLM agents autonomously invent, evolve, and share compact Language Symbolism Frameworks (LSFs), while a latent-free router adaptively selects and composes these languages per query to optimize the accuracy-token trade-off. Unlike prompt optimization that refines surface instructions, CLSR treats each LSF as a reusable symbolic protocol with compact symbols, usage rules, and a message-passing contract, and improves it through an evolutionary loop driven by correctness and token cost. At inference time, the router may invoke a single low-cost LSF call, ensemble multiple LSFs, or execute a multi-round LSF composition protocol on harder queries. Across challenging benchmarks, CLSR reduces latency-oriented generated token completion by $3\sim 6\times$ compared to standard CoT while maintaining accuracy. We further derive an information-theoretic lower bound on token cost under arbitrary symbolism and show that, under an interpreter-realizability premise, multi-round LSF protocols conditionally subsume program-execution pipelines. Code is publicly available (https://github.com/pzqpzq/LSF_MDia).

View source

Similar papers

Preprint Jul 2026

TypeGo: An OS Runtime for Embodied Agents

Large language models (LLMs) can plan behavior for embodied agents from natural language, but treating the LLM as a request/response oracle on the critical path is fundamentally at odds with real-time control and concurrent goals. We argue for an operating-system-style runtime for embodied agents, and instantiate this idea in an early prototype, TypeGo. TypeGo structures LLM-based planning as asynchronous loops at multiple timescales that overlap with execution, and manages the agent's physical body like an OS manages hardware: the Skill Kernel arbitrates typed physical subsystems among concurrent per-task processes, a scheduler preempts them and resumes or replaces each by source, and speculative skill streaming hides LLM latency behind ongoing motion, while a fast first-action path yields visible feedback within a second. Users program behavior through natural language prescriptions that TypeGo dispatches to the LLM-based planners or compiles into low-latency interrupt handlers. Our prototype of Kalos, a Unitree Go2 quadruped, provides preliminary evidence for the design: in our current task suite, it cuts per-step delay by 50% over step-by-step planning and time-to-first-action by 73% over monolithic planning, while admitting concurrent tasks at low scheduling overhead.

Guojun Chen, A. Schott, Lin Zhong · 0 citations
Preprint Jul 2026

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference

Results show that learned token-level handoffs can reduce LLM use while preserving strong reasoning performance, and show that learned token-level handoffs can reduce LLM use while preserving strong reasoning performance.

Niqi Lyu, Pengtao Shi, Wei Qiu et al. · 0 citations
Preprint Aug 2026

Chained Recursive Language Models for Multi-Iteration Reasoning

This work proposes Chained Recursive Language Models (Chained RLM), an inference-time architecture, in which the same underlying model is called repeatedly as a sequence of fresh reasoning roots, and studies when fresh-context artifact continuation gives a measurable gain in accuracy over direct LLM answering even with recursive tool-calling.

Purbesh Mitra, S. Ulukus · 0 citations
Open access Jun 2026

Small Language Models and Spec-Driven Development for High-Accuracy Agentic AI Systems

A hybrid architecture in which a lightweight dispatcher takes in structured tasks, which are routed to specialist LoRA fine-tuned SLMs, suggesting that specialized SLMs with explicit specifications and selective LLM fallback are a practical, scalable, and low-energy foundation for next-gen high-accuracy agentic AI systems.

Guruprasath Sankaran · 0 citations
Preprint Jul 2026

PoTRE: Test-Time Reasoning inspired by Cognitive Heterogeneity

PoTRE (Poly-Topological Reasoning Ensembles), a heterogeneous framework that decouples inference into four agents that achieves improved reasoning performance using similar or fewer inference tokens compared to heavily scaled homogeneous baselines is introduced.

Anmol Kankariya, Sercan Ö. Arik · 0 citations
Jun 2026

QueenBee Planner: Skill-Evolving Communication Topologies for Token-Efficient LLM Multi-Agent Systems

QueenBee Planner is introduced, a framework that treats inter-agent communication topology as a retrievable and self-improving design skill and suggests that multi-agent systems can learn reusable architectural design knowledge rather than merely memorizing task answers.

Cong Tian, Yuhang Yao, Jiaming Cui · 1 citation