Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.05657 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911654892011520 |
|---|---|
| author | Talluri, Abhijit Anne, Pujith Pendiyala, Bhagavan Choudary Chilukuri, Raghavendra |
| author_facet | Talluri, Abhijit Anne, Pujith Pendiyala, Bhagavan Choudary Chilukuri, Raghavendra |
| contents | Multi-agent LLM systems for code generation face a fundamental routing problem: the optimal orchestration topology depends on the structural complexity of the code under modification, yet existing systems select topologies without consulting the codebase. We present Retrieval-Guided Adaptive Orchestration (RGAO), an architecture that closes this loop by extracting a structural complexity vector from a hierarchical code index before selecting the orchestration topology. RGAO operates within Code-Agent, a multi-agent framework whose sub-agents are governed by formal contracts with six-dimensional budget vectors. Our headline contribution is the composition of two previously separate lines of work -- complexity-conditioned LLM routing and formal resource algebras -- yielding a property neither admits alone: provable budget conservation under retrieval-conditioned dynamic topology selection. Concretely we contribute: (1) a complexity-conditioned topology router that reduces proxy-measured misrouting from 30.1% to 8.2%; (2) a budget algebra with a structural-induction conservation theorem; and (3) a hierarchical code retrieval engine. Empirical evaluation demonstrates sub-millisecond DAG construction and linear tree-index scalability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_05657 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Retrieval-Conditioned Topology Selection with Provable Budget Conservation for Multi-Agent Code Generation Talluri, Abhijit Anne, Pujith Pendiyala, Bhagavan Choudary Chilukuri, Raghavendra Artificial Intelligence Multiagent Systems I.2.11; D.2 Multi-agent LLM systems for code generation face a fundamental routing problem: the optimal orchestration topology depends on the structural complexity of the code under modification, yet existing systems select topologies without consulting the codebase. We present Retrieval-Guided Adaptive Orchestration (RGAO), an architecture that closes this loop by extracting a structural complexity vector from a hierarchical code index before selecting the orchestration topology. RGAO operates within Code-Agent, a multi-agent framework whose sub-agents are governed by formal contracts with six-dimensional budget vectors. Our headline contribution is the composition of two previously separate lines of work -- complexity-conditioned LLM routing and formal resource algebras -- yielding a property neither admits alone: provable budget conservation under retrieval-conditioned dynamic topology selection. Concretely we contribute: (1) a complexity-conditioned topology router that reduces proxy-measured misrouting from 30.1% to 8.2%; (2) a budget algebra with a structural-induction conservation theorem; and (3) a hierarchical code retrieval engine. Empirical evaluation demonstrates sub-millisecond DAG construction and linear tree-index scalability. |
| title | Retrieval-Conditioned Topology Selection with Provable Budget Conservation for Multi-Agent Code Generation |
| topic | Artificial Intelligence Multiagent Systems I.2.11; D.2 |
| url | https://arxiv.org/abs/2605.05657 |