CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges
read the original abstract
Large Language Models (LLMs) have shown promise in automated code generation but typically excel only in simpler tasks such as generating standalone code units. Real-world software development, however, often involves complex code repositories (named repo) with complex dependencies and extensive documentation. To fill this gap, our research pivots towards evaluating LLMs in a more realistic setting -- real-world repo-level code generation. We introduce CodeAgentBench, a manually curated benchmark for repo-level code generation. This benchmark comprises five high-quality Python projects, encompassing a total of 101 samples. We assess nine leading LLMs on repo-level tasks and observe a decline in their performance. To tackle this, we present CodeAgent, a novel LLM-based agent framework that employs external tools for effective repo-level code generation. CodeAgent integrates five programming tools, enabling interaction with software artifacts for information retrieval, code symbol navigation, and code testing. We implement four agent strategies to optimize these tools' usage. Our experiments on CodeAgentBench show that CodeAgent enhances LLM performance significantly, with improvements ranging from 18.1\% to 250\%. Further tests on the HumanEval benchmark confirm CodeAgent's adaptability and efficacy across various code generation tasks. Notably, CodeAgent outperforms commercial products like Github Copilot, showcasing superior accuracy and efficiency. These results demonstrate CodeAgent's robust capabilities in code generation, highlighting its potential for real-world repo-level coding challenges.
This paper has not been read by Pith yet.
Forward citations
Cited by 23 Pith papers
-
Sakura: An Approach for Generating Complex Tests from Natural Language Test Descriptions
Sakura is a multi-agent system that generates structurally complex tests from NL descriptions, achieving 50-78% higher compilability and 38-66% higher coverage overlap than baselines on 1,464 scenarios from 20 Apache ...
-
IdleSpec: Exploiting Idle Time via Speculative Planning for LLM Agents
IdleSpec improves LLM agent accuracy by generating and aggregating speculative plans during idle time between tool calls and observations using complementary drafting strategies.
-
Beyond Translation Accuracy: Addressing False Failures in LLM-Based Code Translation
Many reported failures in LLM-based code translation are false negatives due to evaluation pipeline issues such as improper compilation flags, missing library links, and unconfigured runtime environments rather than i...
-
Context-Augmented Code Generation: How Product Context Improves AI Coding Agent Decision Compliance by 49%
Adding product context retrieval to AI coding agents raises decision compliance from 46% to 95% on a new benchmark of 8 tasks with 41 weighted decision points.
-
Beyond Verifiable Rewards: Rubric-Based GRM for Reinforced Fine-Tuning SWE Agents
A rubric-based generative reward model improves reinforced fine-tuning of SWE agents by supplying richer behavioral guidance than binary terminal rewards alone.
-
SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents
SkillJect automates creation of poisoned skills that outperform manual prompt injection by embedding payloads in helper scripts and using multi-agent feedback to refine instructions.
-
In Line with Context: Repository-Level Code Generation via Context Inlining
InlineCoder reframes repository-level code generation as function-level coding by using a draft anchor to inline the target function into its call graph for upstream usage and downstream dependency context.
-
FaSTA$^*$: Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing
FaSTA* combines LLM fast planning with A* search and inductive subroutine mining to create an efficient agent for multi-turn image editing tasks.
-
Where Do CoT Training Gains Land in LLM based Agents?
CoT training in LLM agents improves prompt-action quality more than the advantage of generated reasoning, and selectively masking action supervision improves out-of-domain generalization.
-
Diagnosing Task Insensitivity in Language Agents
The paper diagnoses task insensitivity in LLM agents as a cause of weak OOD generalization, links it to attention drift, and proposes Task-Perturbed NLL Optimization as a contrastive regularizer to improve task dependence.
-
MAVIS: Multi-Agent Video Retrieval via Structured Video Understanding
MAVIS introduces a multi-agent framework that parses videos into a structured semantic library and uses logic-aware debate among agents to retrieve relevant videos competitively without task-specific fine-tuning.
-
Contextualized Code Pretraining for Code Generation
Introduces contextualized code pretraining with caller-callee pairs from static analysis to train CallerGen models that outperform baselines on the new CallerEval benchmark.
-
Revisiting DAgger in the Era of LLM-Agents
DAgger-style training with turn-level policy interpolation raises 4B and 8B LLM agents to 27.3% and 29.8% on SWE-bench Verified, beating several larger published systems.
-
RealBench: A Repo-Level Code Generation Benchmark Aligned with Real-World Software Development Practices
RealBench is a new repo-level code generation benchmark that adds UML diagrams to natural language specs, showing LLMs struggle more at full repositories, create modules with errors, and perform best with whole-repo g...
-
MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage Generation
MM-WebAgent is a hierarchical multimodal agent that coordinates AIGC tools through planning and iterative self-reflection to generate coherent, visually consistent webpages and outperforms baselines on a new benchmark.
-
TokenCake: A KV-Cache-centric Serving Framework for LLM-based Multi-Agent Applications
TokenCake introduces agent-aware temporal and spatial schedulers for KV cache management in LLM multi-agent serving, claiming over 47% lower end-to-end latency and up to 16.9% better GPU memory utilization than vLLM o...
-
Beyond Translation Accuracy: Addressing False Failures in LLM-Based Code Translation
A large-scale study finds that many LLM code translation failures are false negatives due to improper evaluation configurations rather than incorrect translations.
-
RealBench: A Repo-Level Code Generation Benchmark Aligned with Real-World Software Development Practices
RealBench is a repo-level code generation benchmark pairing UML diagrams with natural language requirements, revealing that LLMs perform significantly worse on realistic repo-level tasks than existing benchmarks suggest.
-
AblateCell: A Reproduce-then-Ablate Agent for Virtual Cell Repositories
AblateCell reproduces baselines in three single-cell perturbation repositories with 88.9% success and recovers ground-truth critical components with 93.3% accuracy via closed-loop ablation.
-
Learning Project-wise Subsequent Code Edits via Interleaving Neural-based Induction and Tool-based Deduction
TRACE improves project-wise subsequent code editing by interleaving neural-based induction for semantic edits and tool-based deduction for syntactic edits.
-
Retrieval-Augmented Generation for AI-Generated Content: A Survey
A survey classifying RAG foundations for AIGC, summarizing enhancements, cross-modal applications, benchmarks, limitations, and future directions.
-
LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review
A review of 114 studies classifies motivations into nine categories, analyzes common models and benchmarks, synthesizes challenges into six categories with 26 subcategories and solutions, and identifies six future res...
-
A Survey on the Memory Mechanism of Large Language Model based Agents
A systematic review of memory designs, evaluation methods, applications, limitations, and future directions for LLM-based agents.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.