Context Engineering for Multi-Agent LLM Code Assistants

Context Engineering for Multi-Agent LLM Code Assistants

Context Engineering for Multi-Agent LLM Code Assistants

Using Elicit, NotebookLM, ChatGPT, and Claude Code

Muhammad Haseeb • Virginia Tech • August 2025

description
Abstract

Large Language Models (LLMs) have shown promise in automating code generation, yet they struggle with complex, multi-file projects due to context limitations. We propose a novel context engineering workflow combining multiple AI components: an Intent Translator (GPT-5), Elicit-powered semantic literature retrieval, NotebookLM-based document synthesis, and a Claude Code multi-agent system. Our approach leverages intent clarification, retrieval-augmented generation, and specialized sub-agents to significantly improve accuracy and reliability of code assistants in real-world repositories.

error_outline
Problem Statement

LLMs struggle with complex, multi-file projects due to context limitations

Single-agent approaches often produce incomplete or incorrect solutions

Knowledge gaps when confronted with unfamiliar APIs or frameworks

Static context files cannot capture all relevant details for every possible task

lightbulb
Proposed Solution

Novel context engineering workflow combining multiple AI components

Intent clarification, retrieval-augmented generation, and specialized sub-agents

Orchestrated via Claude's agent framework with role decomposition

Targeted context injection for better adherence to project context

integration_instructions
Key Components

translate
Intent Translator (GPT-5)

Clarifies user requirements and translates them into structured task specifications for the multi-agent system.

search
Elicit Semantic Retrieval

Performs semantic search over academic papers, documentation, and Q&A resources to inject domain knowledge.

summarize
NotebookLM Synthesis

Creates concise summaries of retrieved materials and answers follow-up questions for detailed understanding.

groups
Claude Code Multi-Agent

Orchestrates specialized sub-agents (planner, coder, tester, reviewer) with vector database for code context.

insights
Results & Performance

3.5×

Higher single-shot success rate

42%

Better context adherence

180K

Lines of code in test repository

90%

Reduction in human intervention

compare
Comparison with Other Frameworks

Framework
Approach
Success Rate
Key Advantage

Our System
Context engineering + multi-agent
68.2%
Targeted context injection

CodePlan
Multi-step planning
45.3%
Structured approach

MASAI
Modular architecture
28.3%
Specialized sub-agents

HyperAgent
Team of agents
52.7%
Human-like workflow

rocket_launch
Implications & Future Work

Production-ready deployment with CI/CD integration

Context management strategies for large-scale projects

Cost optimization for multi-agent systems

Extension to other software engineering domains