What Do AI Agents Actually Change? An Empirical Taxonomy of Mutation Patterns in Performance-Improving Pull Requests

• URL: http://arxiv.org/abs/2607.05666v1
• Date: Mon, 06 Jul 2026 22:15:54 GMT
• Title: What Do AI Agents Actually Change? An Empirical Taxonomy of Mutation Patterns in Performance-Improving Pull Requests
• Abstract summary: AI coding agents are black boxes: we cannot inspect how they generate code, but we can inspect what they change.<n>This distinction matters for search-based software engineering (SBSE), where techniques such as genetic improvement depend on mutation operators that reflect how code is actually transformed.<n>We classify 1,254 performance-relevant diff hunks from 216 of these PRs, spanning five agent systems.
• Score: 39.407739937584104
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: AI coding agents are black boxes: we cannot inspect how they generate code, but we can inspect what they change. This distinction matters for search-based software engineering (SBSE), where techniques such as genetic improvement (in the performance-optimisation application we study) depend on mutation operators that reflect how code is actually transformed. Fewer than 1% of the 33,596 agent PRs in AIDev-pop target performance, making each case a rare window into otherwise opaque agent behaviour. We classify 1,254 performance-relevant diff hunks from 216 of these PRs, spanning five agent systems, against the 18-category syntactic mutation taxonomy of Even-Mendoza et al. (2025) using a dual-LLM intersection pipeline. Three categories dominate: name modification (37.0%), object creation (26.4%), and type change (22.7%), a profile markedly different from prior GI corpora where no change accounted for 84%. Each agent's deployed system commits to a distinctive mutation vocabulary, and each performance strategy activates a largely disjoint category subset. Agent identity and target strategy are therefore informative priors that narrow the effective SBSE operator space. Replication package: https://github.com/5uper6rain/ssbse-challenge-2026

Related papers

• A Few Pages of Markdown: Committed AI Configuration and Lower Quality Cost after Coding-Agent Adoption [33.31789388282026]
  Coding agents increase development velocity but also technical debt.<n>Prior work reports only average effects across adopters, hiding wide differences between teams.<n>We introduce RAMP, a four-level cumulative maturity model grounded in version-controlled artifacts that teams commit to configure AI tools.
  arXiv  Detail & Related papers  (2026-08-26T00:00:48Z)
• ClawArena: Benchmarking AI Agents in Evolving Information Environments [61.664633997138004]
  ClawArena is a benchmark for evaluating AI agents in evolving information environments.<n>Each scenario maintains a complete hidden ground truth while exposing the agent only to noisy, partial, and sometimes contradictory traces.<n> evaluation is organized around three coupled challenges: multi-source conflict reasoning, dynamic belief revision, and implicit personalization.
  arXiv  Detail & Related papers  (2026-04-05T17:55:23Z)
• AgentSZZ: Teaching the LLM Agent to Play Detective with Bug-Inducing Commits [14.213358505741105]
  AgentSZZ is an agent-based framework for identifying bug-inducing commits.<n>Unlike prior methods, AgentSZZ integrates task-specific tools, domain knowledge, and a ReAct-style loop to enable adaptive and causal tracing of bugs.<n>Experiments show that AgentSZZ consistently outperforms state-of-the-art SZZ algorithms across all settings.
  arXiv  Detail & Related papers  (2026-04-03T02:54:02Z)
• TRAJEVAL: Decomposing Code Agent Trajectories for Fine-Grained Diagnosis [23.834704102474927]
  Code agents can resolve GitHub issues, yet when they fail, current evaluation provides no visibility into where or why.<n>We introduce TRAJEVAL, a diagnostic framework that decomposes agent trajectories into three interpretable stages.<n>We validate that these diagnostics are predictive, achieving model-level Pass@1 prediction within 0.87-2.1% MAE.
  arXiv  Detail & Related papers  (2026-03-25T05:27:03Z)
• How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull Requests [0.0]
  We analyze 24,014 merged Agentic PRs (440,295 commits) and 5,081 merged Human PRs (23,242 commits)<n>Agentic PRs differ substantially from Human PRs in commit count (Cliff's $= 0.5429$) and show moderate differences in files touched and deleted lines.<n>These findings provide a large-scale empirical characterization of how AI coding agents contribute to open source development.
  arXiv  Detail & Related papers  (2026-01-24T20:27:04Z)
• SCOPE: Prompt Evolution for Enhancing Agent Effectiveness [53.75986399936395]
  Large Language Model (LLM) agents are increasingly deployed in environments that generate massive, dynamic contexts.<n>While agents have access to this context, their static prompts lack the mechanisms to manage it effectively.<n>We introduce textbfSCOPE (Self-evolving Context Optimization via Prompt Evolution)<n>We propose a Dual-Stream mechanism that balances tactical specificity (resolving immediate errors) with strategic generality (evolving long-term principles)
  arXiv  Detail & Related papers  (2025-12-17T12:25:05Z)
• Towards a Science of Scaling Agent Systems [79.64446272302287]
  We formalize a definition for agent evaluation and characterize scaling laws as the interplay between agent quantity, coordination structure, modelic, and task properties.<n>We derive a predictive model using coordination metrics, that cross-validated R2=0, enabling prediction on unseen task domains.<n>We identify three effects: (1) a tool-coordination trade-off: under fixed computational budgets, tool-heavy tasks suffer disproportionately from multi-agent overhead, and (2) a capability saturation: coordination yields diminishing or negative returns once single-agent baselines exceed 45%.
  arXiv  Detail & Related papers  (2025-12-09T06:52:21Z)
• Learning When to Switch: Adaptive Policy Selection via Reinforcement Learning [0.0]
  This work demonstrates how an agent can dynamically transition between systematic exploration (coverage) and goal-directed pathfinding (convergence) to improve task performance.<n>Unlike fixed-threshold approaches, the agent uses Q-learning to adapt switching behavior based on coverage percentage and distance to goal.<n>Results show 23-55% improvements in completion time, 83% reduction in runtime variance, and 71% improvement in worst-case scenarios.
  arXiv  Detail & Related papers  (2025-12-06T02:50:32Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving [62.71545696485824]
  We introduce AGENT KB, a universal memory infrastructure enabling seamless experience sharing across heterogeneous agent frameworks without retraining.<n>AGENT KB aggregates trajectories into a structured knowledge base and serves lightweight APIs.<n>We validate AGENT across major frameworks on GAIA, Humanity's Last Exam, GPQA, and SWE-bench.
  arXiv  Detail & Related papers  (2025-07-08T17:59:22Z)

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.