REVIEW 19 cited by
A Survey of Large Language Models for Code: Evolution, Benchmarking, and Future Trends
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
A Survey of Large Language Models for Code: Evolution, Benchmarking, and Future Trends
read the original abstract
General large language models (LLMs), represented by ChatGPT, have demonstrated significant potential in tasks such as code generation in software engineering. This has led to the development of specialized LLMs for software engineering, known as Code LLMs. A considerable portion of Code LLMs is derived from general LLMs through model fine-tuning. As a result, Code LLMs are often updated frequently and their performance can be influenced by the base LLMs. However, there is currently a lack of systematic investigation into Code LLMs and their performance. In this study, we conduct a comprehensive survey and analysis of the types of Code LLMs and their differences in performance compared to general LLMs. We aim to address three questions: (1) What LLMs are specifically designed for software engineering tasks, and what is the relationship between these Code LLMs? (2) Do Code LLMs really outperform general LLMs in software engineering tasks? (3) Which LLMs are more proficient in different software engineering tasks? To answer these questions, we first collect relevant literature and work from five major databases and open-source communities, resulting in 134 works for analysis. Next, we categorize the Code LLMs based on their publishers and examine their relationships with general LLMs and among themselves. Furthermore, we investigate the performance differences between general LLMs and Code LLMs in various software engineering tasks to demonstrate the impact of base models and Code LLMs. Finally, we comprehensively maintained the performance of LLMs across multiple mainstream benchmarks to identify the best-performing LLMs for each software engineering task. Our research not only assists developers of Code LLMs in choosing base models for the development of more advanced LLMs but also provides insights for practitioners to better understand key improvement directions for Code LLMs.
Forward citations
Cited by 19 Pith papers
-
PassNet: Scaling Large Language Models for Graph Compiler Pass Generation
PassNet provides a dataset of 18K graphs and PassBench for LLM-generated compiler passes, with fine-tuned models achieving 2.67x gains on long-tail tasks where TorchInductor underperforms.
-
Reversa: A Reverse Documentation Engineering Framework for Converting Legacy Software into Operational Specifications for AI Agents
Reversa is a reverse documentation engineering framework that deploys a multi-agent pipeline to extract implicit rules from legacy software and produce traceable specifications with confidence scores and explicit gaps...
-
Can LLMs Deobfuscate Binary Code? A Systematic Analysis of Large Language Models into Pseudocode Deobfuscation
LLM deobfuscation of binaries to pseudocode depends more on reasoning ability and task-specific fine-tuning than on model size, with reasoning models showing robustness across ISAs and obfuscation levels on the new Bi...
-
PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents
A multi-agent repair framework that samples multiple edit locations and iteratively reflects on patch attempts reaches 76.0% Pass@1 on SWE-bench-Verified, up to a 7.8% relative gain over SWE-agent.
-
Plainbook: Data Science, in Plain Language
Plainbook makes data-science notebooks natural-language-first by preserving cell descriptions, generating code via AI, enforcing linear execution via a checkpointing kernel, and adding value-centered cell and global tests.
-
Test Case Selection for Deep Neural Networks: A Replication Study on LLMs for Code
Replication of TCS strategies on 17 LLM instances across three code tasks shows only partial generalization from vision DNN results, with uncertainty features aiding early failure discovery and representation features...
-
AI-Generated Smells: An Analysis of Code and Architecture in LLM and Agent-Driven Development
More capable LLMs and agents generate code with greater volume and architectural decay, following a Volume-Quality Inverse Law that neither functional correctness nor prompting mitigates.
-
Leveraging Mathematical Reasoning of LLMs for Efficient GPU Thread Mapping
Large language models derive exact analytical GPU thread mappings for complex 2D/3D domains and fractals via in-context learning, outperforming symbolic regression and enabling up to thousands-fold speedups and energy...
-
Compiling Code LLMs into Lightweight Executables
Ditto quantizes Code LLMs with K-Means codebooks and compiles inference via LLVM-BLAS replacement to deliver up to 10.5x faster, 6.4x smaller, and 10.5x lower-energy execution on commodity hardware while losing only 0...
-
Qiskit Code Migration with LLMs
A taxonomy-guided RAG system with LLMs reduces hallucinations and improves migration suggestions for Qiskit code compared to unconstrained retrieval.
-
DeltaMCP: Incremental Regeneration via Spec-Aware Transformation for MCP servers
DeltaMCP introduces specification-aware incremental regeneration to keep MCP servers synchronized with evolving OpenAPI specifications.
-
A Tertiary Review of Large Language Model-Based Code Generating Tasks: Trends, Challenges, and Future Directions
A synthesis of 30 secondary studies finds strong benchmark accuracy for LLM code generation but weak real-world generalization, fragile robustness, pervasive efficiency issues, and under-reported bias, calling for dom...
-
Understanding Conversational Patterns in Multi-agent Programming: A Case Study on Fibonacci Game Development
Case study of 12 LLM agent pairs on Fibonacci game development finds only DeepSeek-R1:DeepSeek-R1 converges correctly from the first iteration while others either diverge or fail to converge.
-
Combining Static Code Analysis and Large Language Models Improves Correctness and Performance of Algorithm Recognition
Hybrid LLM plus static analysis for algorithm recognition in code cuts required model calls by 72-97% and lifts F1-scores by as much as 12 points.
-
Compiling Code LLMs into Lightweight Executables
Ditto quantizes Code LLMs with per-block K-Means codebooks and compiles GEMV into BLAS calls, claiming up to 10.5× faster, 6.4× leaner local inference with ~0.27% pass@1 loss.
-
Are Decoder-Only Large Language Models the Silver Bullet for Code Search?
Fine-tuned decoder-only LLMs achieve up to 40.4% higher MAP than UniXcoder on CoSQA+ for code search, with non-monotonic size scaling and data composition sensitivity.
-
CodePori: Large-Scale System for Autonomous Software Development Using Multi-Agent Technology
CodePori is a multi-agent LLM system for code generation whose participant evaluation identifies practical challenges like memory limits and hallucinations missed by binary benchmarks.
-
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.