Retrieval-Conditioned Topology Selection with Provable Budget Conservation for Multi-Agent Code Generation

2026-05-07 · Abhijit Talluri, Pujith Anne, Bhagavan Choudary Pendiyala, Raghavendra Chilukuri arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.05657

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

AdaptOrch: Task-Adaptive Multi-Agent Orchestration in the Era of LLM Performance Convergence

2026-02-18 · Geunbin Yu arxiv

As large language models from diverse providers converge toward comparable benchmark performance, the traditional paradigm of selecting a single best model per task yields diminishing returns. We argue that orchestration…

CREST: Curvature-Regulated Event-Centric Sampling for Efficient Long-Video Understanding

2026-05-09 · Mehrajul Abadin Miraj, Abdul Mohaimen Al Radi, Shariful Islam Rayhan, Md. Tanvir Alam 외 arxiv

Selecting informative frames from long videos is a combinatorial problem that existing methods address either through efficient heuristics without explicit modeling of query-conditioned temporal structure, or through mul…

Budget-Constrained Embodied Perception: Four Resource Walls and a Pre-Registered Evaluation of Access-Structured Perception on Open Models at less than 31B

2026-08-24 · Defu Lin, Wenhui Chen, Ziyao Lin, Jianlin Chen 외 arxiv

Embodied multimodal agents must answer from growing observation streams under a fixed per-decision token budget. We formalize this constraint through four resource walls: a perceptual Shannon wall for bounded state, a ho…

Structure and Diversity Aware Context Bubble Construction for Enterprise Retrieval Augmented Systems

2026-01-15 · Amir Khurshid, Abhishek Sehgal arxiv

Large language model (LLM) contexts are typically constructed using retrieval-augmented generation (RAG), which involves ranking and selecting the top-k passages. The approach causes fragmentation in information graphs i…

SearchSkill: Teaching LLMs to Use Search Tools with Evolving Skill Banks

2026-05-09 · Jinchao Hu, Meizhi Zhong, Kehai Chen, Min Zhang arxiv

Teaching language models to use search tools is not only a question of whether they search, but also of whether they issue good queries. This is especially important in open-domain question answering, where broad or copi…

Open-Domain Question Answering