Code Change Characteristics and Description Alignment: A Comparative Study of Agentic versus Human Pull Requests

• URL: http://arxiv.org/abs/2601.17627v1
• Date: Sat, 24 Jan 2026 23:33:07 GMT
• Title: Code Change Characteristics and Description Alignment: A Comparative Study of Agentic versus Human Pull Requests
• Abstract summary: We analyze 33,596 agent-generated PRs and 6,618 human PRs to compare code-change characteristics and message quality.<n>Agents generate stronger commit-level messages but lag humans at PR-level summarization.<n>These findings highlight a gap between agents' micro-level precision and macro-level communication.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: AI coding agents can autonomously generate pull requests (PRs), yet little is known about how their contributions compare to those of humans. We analyze 33,596 agent-generated PRs (APRs) and 6,618 human PRs (HPRs) to compare code-change characteristics and message quality. We observe that APR-introduced symbols (functions and classes) are removed much sooner than those in HPRs (median time to removal 3 vs. 34 days) and are also removed more often (symbol churn 7.33% vs. 4.10%), reflecting a focus on other tasks like documentation and test updates. Agents generate stronger commit-level messages (semantic similarity 0.72 vs. 0.68) but lag humans at PR-level summarization (PR-commit similarity 0.86 vs. 0.88). Commit message length is the best predictor of description quality, indicating reliance on individual commits over full-PR reasoning. These findings highlight a gap between agents' micro-level precision and macro-level communication, suggesting opportunities to improve agent-driven development workflows.

Related papers

• Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems [67.04448659688579]
  We develop a query-independent 16-entry codebook that ranks the top decoded candidates in a single batched forward pass.<n>With no iterative search and no message passing at test time, Codebook Agent is the most accurate method on all six benchmarks.
  arXiv  Detail & Related papers  (2026-09-02T08:10:22Z)
• Fantastic Adaptive Taxonomies and How to Use Them [100.20614173157708]
  AdaMAST converts execution traces into a compact, evidence-grounded failure taxonomy.<n>No code is hand-authored, no trace human-annotated.<n>In agent-system search, taxonomy-coded diagnoses of failed candidates outperform free-form.
  arXiv  Detail & Related papers  (2026-07-17T17:41:16Z)
• SWE-chat: Coding Agent Interactions From Real Users in the Wild [70.18158706281724]
  SWE-chat is the first large-scale dataset of real coding agent sessions collected from open-source developers in the wild.<n>The dataset currently contains 6,000 sessions, comprising more than 63,000 user prompts and 355,000 agent tool calls.
  arXiv  Detail & Related papers  (2026-04-22T17:08:19Z)
• 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)
• Humans Integrate, Agents Fix: How Agent-Authored Pull Requests Are Referenced in Practice [4.359007050137919]
  We introduce a taxonomy to characterize the intent of agent-authored PR references across Human-to-Agent and Agent-to-Agent interactions.<n>Our analysis shows that while humans initiate most references to agent-authored PRs, a substantial portion of these interactions are AI-assisted.<n>We find that referencing/referenced PRs are associated with substantially longer lifespan and review times compared to isolated PRs.
  arXiv  Detail & Related papers  (2026-04-05T11:04:46Z)
• Safer Builders, Risky Maintainers: A Comparative Study of Breaking Changes in Human vs Agentic PRs [0.991629944808926]
  We conduct a comparative analysis of 7,191 agent-generated PRs with 1402 human-authored PRs from Python repositories.<n>We show that AI agents introduce fewer breaking changes overall than humans (3.45% vs. 7.40%) in code generation tasks.<n>Agents exhibit substantially higher risk during maintenance tasks, with changes introducing breaking changes at rates of 6.72% and 9.35%, respectively.
  arXiv  Detail & Related papers  (2026-03-29T05:15:13Z)
• Why Agentic-PRs Get Rejected: A Comparative Study of Coding Agents [0.0]
  We show that Pull Requests produced using coding agents (Agentic-PRs) are accepted less often than PRs that are not labeled as agentic (Human-PRs)<n>A large proportion of rejected PRs lack explicit feedback, making their rejection reasons difficult to determine.
  arXiv  Detail & Related papers  (2026-02-04T05:24:18Z)
• Beyond Bug Fixes: An Empirical Investigation of Post-Merge Code Quality Issues in Agent-Generated Pull Requests [4.744786007044749]
  We analyze 1,210 merged agent-generated bug-fix PRs from Python repositories in the AIDev dataset.<n>Our results show that apparent differences in raw issue counts across agents largely disappear after normalizing by code churn.<n>Across all agents, code smells dominate, particularly at critical and major severities, while bugs are less frequent but often severe.
  arXiv  Detail & Related papers  (2026-01-27T22:55:05Z)
• 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)
• Analyzing Message-Code Inconsistency in AI Coding Agent-Authored Pull Requests [5.885226503818935]
  Pull request descriptions generated by AI coding agents are the primary channel for communicating code changes to human reviewers.<n>We analyzed 23,247 agentic PRs across five agents using PR message-code inconsistency (PR-MCI)<n>High-MCI PRs had 51.7% lower acceptance rates and took 3.5x longer to merge.
  arXiv  Detail & Related papers  (2026-01-08T12:31:02Z)
• Early-Stage Prediction of Review Effort in AI-Generated Pull Requests [0.0]
  We analyze 33,707 agent-authored PRs from the AIDev dataset across 2,807 repositories.<n>We propose a Circuit Breaker triage model that predicts high-review-effort PRs at creation time.
  arXiv  Detail & Related papers  (2026-01-02T17:18:01Z)
• Security in the Age of AI Teammates: An Empirical Study of Agentic Pull Requests on GitHub [4.409447722044799]
  This study aims to characterize how autonomous coding agents contribute to software security in practice.<n>We conduct a large-scale empirical analysis of agent-authored PRs using the AIDev dataset.<n>We then analyze prevalence, acceptance outcomes, and review latency across autonomous agents, programming ecosystems, and types of code changes.
  arXiv  Detail & Related papers  (2026-01-01T21:14:11Z)
• Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation [87.47155146067962]
  We provide a standardized evaluation harness that orchestrates parallel evaluations across hundreds of tasks.<n>We conduct three-dimensional analysis spanning models, scaffolds, and benchmarks.<n>Our analysis reveals surprising insights, such as higher reasoning effort reducing accuracy in the majority of runs.
  arXiv  Detail & Related papers  (2025-10-13T22:22:28Z)
• Impatient Users Confuse AI Agents: High-fidelity Simulations of Human Traits for Testing Agents [58.00130492861884]
  TraitBasis is a lightweight, model-agnostic method for systematically stress testing AI agents.<n>TraitBasis learns directions in activation space corresponding to steerable user traits.<n>We observe on average a 2%-30% performance degradation on $tau$-Trait across frontier models.
  arXiv  Detail & Related papers  (2025-10-06T05:03:57Z)
• On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub [6.7302091035327285]
  Large language models (LLMs) are increasingly being integrated into software development processes.<n>The ability to generate code and submit pull requests with minimal human intervention, through the use of autonomous AI agents, is poised to become a standard practice.<n>We empirically study 567 GitHub pull requests (PRs) generated using Claude Code, an agentic coding tool, across 157 open-source projects.
  arXiv  Detail & Related papers  (2025-09-18T08:48:32Z)
• Learning Adaptive Parallel Reasoning with Language Models [70.1745752819628]
  We propose Adaptive Parallel Reasoning (APR), a novel reasoning framework that enables language models to orchestrate both serialized and parallel computations end-to-end.<n> APR generalizes existing reasoning methods by enabling adaptive multi-threaded inference using spawn() and join() operations.<n>A key innovation is our end-to-end reinforcement learning strategy, optimizing both parent and child inference threads to enhance task success rate without requiring predefined reasoning structures.
  arXiv  Detail & Related papers  (2025-04-21T22:29:02Z)
• Group-Adaptive Threshold Optimization for Robust AI-Generated Text Detection [58.419940585826744]
  We introduce FairOPT, an algorithm for group-specific threshold optimization for probabilistic AI-text detectors.<n>We partitioned data into subgroups based on attributes (e.g., text length and writing style) and implemented FairOPT to learn decision thresholds for each group to reduce discrepancy.<n>Our framework paves the way for more robust classification in AI-generated content detection via post-processing.
  arXiv  Detail & Related papers  (2025-02-06T21:58:48Z)
• Dissecting Adversarial Robustness of Multimodal LM Agents [70.2077308846307]
  We manually create 200 targeted adversarial tasks and evaluation scripts in a realistic threat model on top of VisualWebArena.<n>We find that we can successfully break latest agents that use black-box frontier LMs, including those that perform reflection and tree search.<n>We also use ARE to rigorously evaluate how the robustness changes as new components are added.
  arXiv  Detail & Related papers  (2024-06-18T17:32:48Z)
• ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs [61.07130026622437]
  Large Language Models (LLMs) still struggle with natural language reasoning tasks. Motivated by the society of minds, we propose ReConcile. A multi-model multi-agent framework designed as a round table conference among diverse LLM agents.
  arXiv  Detail & Related papers  (2023-09-22T17:12:45Z)

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.