mlsanityData to 14 Oct 2026

Devstral: Fine-tuning Language Models for Coding Agent Applications

arXiv 2509.25193 ↗First posted 8 Aug 2025cs.SE cs.AIcited by 24

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

We introduce Devstral-Small, a lightweight open source model for code agents with the best performance among models below 100B size. In this technical report, we give an overview of how we design and develop a model and craft specializations in agentic software development. The resulting model, Devstral-Small is a small 24B model, fast and easy to serve. Despite its size, Devstral-Small still attains competitive performance compared to models more than an order of magnitude larger.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 10 of its 13 references that are in the map. First posted on arXiv 8 Aug 2025.

Builds on

10 of 13 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Training Software Engineering Agents and Verifiers with SWE-Gym30 Dec
  2. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering6 May
  3. 2024Executable Code Actions Elicit Better LLM Agents1 Feb

Other references · 7

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  3. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  4. 2021Program Synthesis with Large Language Modelscited by 3,637
  5. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  6. 2023Code Llama: Open Foundation Models for Codecited by 2,139
  7. 2024Qwen2.5-Coder Technical Reportcited by 1,203

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 22.

24 papers.

Sort:

By area:

  1. 2026AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agentscited by 38
  2. 2026On Randomness in Agentic Evalscited by 17
  3. 2025QAgent: An LLM-based Multi-Agent System for Autonomous OpenQASM programmingcited by 11
  4. 2026SciCoQA: Quality Assurance for Scientific Paper--Code Alignmentcited by 10
  5. 2026SERA: Soft-Verified Efficient Repository Agentscited by 10
  6. 2026SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understandingcited by 9
  7. 2025Agentic Software Issue Resolution with Large Language Models: A Surveycited by 6
  8. 2026Do Chatbot LLMs Talk Too Much? The YapBench Benchmarkcited by 5
  9. 2026EvoRepair: Enhancing Vulnerability Repair Agents Through Experience-Based Self-Evolutioncited by 2
  10. 2026MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesiscited by 2
  11. 2026Adaptive Hierarchical Evaluation of LLMs and SAST tools for CWE Prediction in Pythoncited by 1
  12. 2026TACTIC-KG: Toward Small Agent Teams for Cyber Threat Intelligence Knowledge Graph Constructioncited by 1
12 more
  1. 2026TRACE-ROUTER: Task-Consistent and Adaptive Online Routing for Agentic AIcited by 1
  2. 2026Simulation Code Generation for Fluid Systems using Large Language Models: Benchmarking Models and Prompting Strategiescited by 1
  3. 2026DataKernelBench: Can LLMs Optimize Database Queries on GPUs?cited by 1
  4. 2026CodeCytos: AI-assisted spatial molecular imaging analysis via code-augmented agent action spacecited by 0
  5. 2026KGVoyager: Knowledge Graph Agnostic Question Answering via Agentic Navigationcited by 0
  6. 2026CS-Guard: Benchmarking LLM Guardrails for Code Generation Securitycited by 0
  7. 2026CodeTS: Verifiable Text-to-Time Series Generation via Executable Codecited by 0
  8. 2026ISA-Bench: A Benchmark for Computational Reasoning Across Instruction Set Architecturescited by 0
  9. 2026APOLO: Automatic Prompt Optimization for Ontology Learningcited by 0
  10. 2026Learning When and How to Intervene: A Hindsight-Distilled Sentinel for Coding Agentscited by 0
  11. 2026AgSpec: Pushing the Limits of Retrieval-Based Speculative Decoding in Coding Agent Pipelinescited by 0
  12. 2026AdaEva: Accelerating LLM-Driven Algorithm Design with Adaptive Partial Evaluationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Rethinking Scale: Deployment Trade-offs of Small Language Models under Agent Paradigms
  2. 2025Small Language Models for Agentic Systems: A Survey of Architectures, Capabilities, and Deployment Trade offs
  3. 2026FormulaCode: Evaluating Agentic Optimization on Large Codebases
  4. 2026Constraint Decay: The Fragility of LLM Agents in Backend Code Generation
  5. 2025TinyLLM: Evaluation and Optimization of Small Language Models for Agentic Tasks on Edge Devices
  6. 2025SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models
  7. 2026ChatDev 2.0: A No-Code Multi-Agent Platform for Developing Everything
  8. 2026Beyond Quantity: Trajectory Diversity Scaling for Code Agents