SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios

• URL: http://arxiv.org/abs/2512.18470v2
• Date: Tue, 23 Dec 2025 19:29:43 GMT
• Title: SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios
• Abstract summary: Existing benchmarks for AI coding agents focus on isolated, single-issue tasks such as fixing a bug or implementing a small feature.<n>We introduce SWE-EVO, a benchmark that evaluates agents on a long-horizon software evolution challenge.<n>Tool comprises 48 evolution tasks that require agents to implement multi-step modifications spanning an average of 21 files.
• Score: 6.776894728701934
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing benchmarks for AI coding agents focus on isolated, single-issue tasks such as fixing a bug or implementing a small feature. However, real-world software engineering is fundamentally a long-horizon endeavor: developers must interpret high-level requirements, plan coordinated changes across many files, and evolve codebases over multiple iterations while preserving existing functionality. We introduce SWE-EVO, a benchmark that evaluates agents on this long-horizon software evolution challenge. Constructed from release notes and version histories of seven mature open-source Python projects, Tool comprises 48 evolution tasks that require agents to implement multi-step modifications spanning an average of 21 files, validated against comprehensive test suites averaging 874 tests per instance. Experiments with state-of-the-art models reveal a striking capability gap: even GPT-5 with OpenHands achieves only a 21 percent resolution rate on Tool, compared to 65 percent on the single-issue SWE-Bench Verified. This demonstrates that current agents struggle with sustained, multi-file reasoning. We also propose Fix Rate, a fine-grained metric that captures partial progress toward solving these complex, long-horizon tasks.

Related papers

• MTAC-IFBench: Benchmarking Instruction-Following in Multi-Turn Agentic Coding [83.0805548642958]
  MTAC-IFBench is a comprehensive benchmark for instruction-following in software development.<n>It features multi-turn progressive software development instructions with diverse constraints spanning 6 primary and 18 secondary categories.<n>MTAC-IFBench identifies significant deficiencies in existing code agents in multi-turn instruction-following, with their performance degrading rapidly as the interaction session grows longer.
  arXiv  Detail & Related papers  (2026-09-14T03:57:37Z)
• SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring [31.684059339633013]
  SWE-Bench ProMax is an expert-curated, multilingual code benchmark of 170 instances drawn from real commits.<n>Every instance undergoes rigorous, multi-stage curation that addresses quality problems identified in prior benchmarks.<n>Experiments with frontier models under two agent scaffolds show that the best model achieves only 41.2% resolve rate.
  arXiv  Detail & Related papers  (2026-08-10T16:23:19Z)
• BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution [59.619780973577434]
  BenchEvolver is a solution-centric evolutionary framework that transforms existing coding problems into harder variants.<n>We show that BenchEvolver can convert saturated benchmarks into frontier-level evaluation suites and reusable training signal.
  arXiv  Detail & Related papers  (2026-05-31T15:12:16Z)
• RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades [32.04167306620878]
  We present RoadmapBench, a benchmark of 115 long-horizon coding tasks grounded in real open-source version upgrades.<n>Each task places the agent on a source-version code snapshot and provides a multi-target roadmap instruction.<n>We find that even the strongest, Claude-Opus-4.7, resolves only 39.1% of tasks, while the weakest iteration achieves merely 5.2%.
  arXiv  Detail & Related papers  (2026-05-15T11:00:33Z)
• WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation [88.10947115397971]
  This work presents WildClawBench, a native-runtime benchmark of 60 human-authored, bilingual, multimodal tasks spanning six thematic categories.<n>Each task averages roughly 8 minutes of wall-clock time and over 20 tool calls.<n> Grading is hybrid, combining deterministic rule-based checks, environment-state auditing of side effects, and an LLM/VLM judge for semantic verification.
  arXiv  Detail & Related papers  (2026-05-11T17:49:43Z)
• SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks [55.76734816061826]
  We introduce SlopCodeBench, a language-agnostic benchmark comprising 20 problems and 93 checkpoints.<n>We track two trajectory-level quality signals: verbosity, the fraction of redundant or duplicated code, and structural erosion.<n>No agent solves any problem end-to-end across 11 models; the highest checkpoint solve rate is 17.2%.
  arXiv  Detail & Related papers  (2026-03-25T19:26:44Z)
• EvoClaw: Evaluating AI Agents on Continuous Software Evolution [47.49468375065129]
  We introduce DeepCommit, an agentic pipeline that reconstructs verifiable Milestone DAGs from noisy commit logs.<n>These executable sequences enable EvoClaw, a novel benchmark that requires agents to sustain system integrity and limit error accumulation.
  arXiv  Detail & Related papers  (2026-03-13T03:20:40Z)
• LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces [65.11019654023978]
  LongCLI-Bench is a benchmark designed to evaluate agentic capabilities across long-horizon, realistic tasks.<n>We curated 20 high-quality, long-horizon tasks from over 1,000 computer science assignments and real-world tasks.<n>Experiments reveal that even state-of-the-art agents achieve pass rates below 20% in LongCLI-Bench.
  arXiv  Detail & Related papers  (2026-02-15T23:12:57Z)
• FeatureBench: Benchmarking Agentic Coding for Complex Feature Development [42.26354337364403]
  FeatureBench is a benchmark designed to evaluate agentic coding performance in end-to-end, feature-oriented software development.<n>It incorporates an execution-based evaluation protocol and a scalable test-driven method that automatically derives tasks from code repositories with minimal human effort.<n> Empirical evaluation reveals that the state-of-the-art agentic model, such as Claude 4.5 Opus, achieves a 74.4% resolved rate on SWE-bench.
  arXiv  Detail & Related papers  (2026-02-11T16:06:32Z)
• AgentStepper: Interactive Debugging of Software Development Agents [14.265317773238529]
  We introduce AgentStepper, the first interactive debugger for software engineering agents.<n>AgentStepper represents trajectories as structured conversations among an LLM, the agent program, and tools.<n>It supports breakpoints, stepwise execution, and live editing of prompts and tool invocations, while capturing and displaying intermediate repository-level code changes.
  arXiv  Detail & Related papers  (2026-02-06T10:44:09Z)
• Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces [126.23612941699565]
  Terminal-Bench 2.0 is a benchmark composed of 89 tasks in computer terminal environments inspired by problems from real world.<n>We show that frontier models and agents score less than 65% on the benchmark.<n>We publish the dataset and evaluation harness to assist developers and researchers in future work at https://www.tbench.ai/.
  arXiv  Detail & Related papers  (2026-01-17T01:29:30Z)
• NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents [79.29376673236142]
  Existing benchmarks fail to rigorously evaluate the long-horizon capabilities required to build complete software systems.<n>We present NL2Repo Bench, a benchmark explicitly designed to evaluate the long-horizon repository generation ability of coding agents.
  arXiv  Detail & Related papers  (2025-12-14T15:12:13Z)
• Multi-Agent Systems for Dataset Adaptation in Software Engineering: Capabilities, Limitations, and Future Directions [8.97512410819274]
  This paper presents the first empirical study on how state-of-the-art multi-agent systems perform in dataset adaptation tasks.<n>We evaluate GitHub Copilot on adapting SE research artifacts from benchmark repositories including ROCODE and LogHub2.0.<n>Results show that current systems can identify key files and generate partial adaptations but rarely produce correct implementations.
  arXiv  Detail & Related papers  (2025-11-26T13:26:11Z)
• The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution [86.4588675093384]
  Toolathlon is a benchmark for language agents offering diverse Apps and tools, realistic environment setup, and reliable execution-based evaluation.<n>This benchmark includes 108 manually sourced or crafted tasks, requiring interacting with multiple Apps over around 20 turns on average to complete.<n>We expect Toolathlon to drive the development of more capable language agents for real-world, long-horizon task execution.
  arXiv  Detail & Related papers  (2025-10-29T17:32:49Z)
• VisCoder2: Building Multi-Language Visualization Coding Agents [63.63232038173407]
  We introduce three complementary resources for advancing visualization coding agents.<n>VisCoder2 significantly outperforms strong open-source baselines and approaches the performance of proprietary models.
  arXiv  Detail & Related papers  (2025-10-24T18:03:57Z)
• UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios [63.67884284105684]
  We introduce textbfUltraHorizon, a novel benchmark that measures the foundational capabilities essential for complex real-world challenges.<n>Agents are designed in long-horizon discovery tasks where they must iteratively uncover hidden rules.<n>Our experiments reveal that LLM-agents consistently underperform in these settings, whereas human participants achieve higher scores.
  arXiv  Detail & Related papers  (2025-09-26T02:04:00Z)
• SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks? [13.645265361867565]
  SWE-Bench Pro builds upon the best practices of SWE-BENCH [25], but is explicitly designed to capture realistic, complex, enterprise-level problems.<n>The benchmark is partitioned into a public set with open access to problems sourced from 11 repositories, a held-out set of 12 repositories and a commercial set of 18 proprietary repositories.<n>In our evaluation of widely used coding models, under a unified scaffold, we observe that their performance on SWE-Bench PRO remains below 25% (Pass@1), with GPT-5 achieving the highest score to date at 23.3%.
  arXiv  Detail & Related papers  (2025-09-21T06:28:17Z)
• Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement [62.94719119451089]
  Lingma SWE-GPT series learns from and simulating real-world code submission activities. Lingma SWE-GPT 72B resolves 30.20% of GitHub issues, marking a significant improvement in automatic issue resolution.
  arXiv  Detail & Related papers  (2024-11-01T14:27:16Z)
• Evaluating Software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios [13.949319911378826]
  This study evaluated 4,892 patches from 10 top-ranked agents on 500 real-world GitHub issues.<n>No single agent dominated, with 170 issues unresolved, indicating room for improvement.<n>Most agents maintained code reliability and security, avoiding new bugs or vulnerabilities.<n>Some agents increased code complexity, many reduced code duplication and minimized code smells.
  arXiv  Detail & Related papers  (2024-10-16T11:33:57Z)
• BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions [72.56339136017759]
  We introduce BigCodeBench, a benchmark that challenges Large Language Models (LLMs) to invoke multiple function calls as tools from 139 libraries and 7 domains for 1,140 fine-grained tasks.<n>Our evaluation shows that LLMs are not yet capable of following complex instructions to use function calls precisely, with scores up to 60%, significantly lower than the human performance of 97%.<n>We propose a natural-language-oriented variant of BigCodeBench, BigCodeBench-Instruct, that automatically transforms the original docstrings into short instructions only with essential information.
  arXiv  Detail & Related papers  (2024-06-22T15:52:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.