Metraipolis › archive › dc_ff83bbdb26de

Evaluating Agentic Code Repair Capabilities in Distributed Systems — arXiv:2608.14863

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.14863
License (as archived): CC0-1.0
Archived: 2026-10-18T17:56:50.484Z
SHA-256 of the archived text: f639739315549e3e1467a2d631fc07c46417cd3a50fdbae83d6b4d1abc1ef240
Stable URL of this page: https://metraipolis.com/documento/dc_ff83bbdb26de

How to cite

Evaluating Agentic Code Repair Capabilities in Distributed Systems — arXiv:2608.14863 — arXiv (en), https://arxiv.org/abs/2608.14863 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff83bbdb26de (Metraipolis archive dc_ff83bbdb26de, sha256 f639739315549e3e1467a2d631fc07c46417cd3a50fdbae83d6b4d1abc1ef240)

BibTeX

@misc{dcff83bbdb26de,
  title = {Evaluating Agentic Code Repair Capabilities in Distributed Systems — arXiv:2608.14863},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14863},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff83bbdb26de; sha256 f639739315549e3e1467a2d631fc07c46417cd3a50fdbae83d6b4d1abc1ef240},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14863. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM-based coding agents have advanced rapidly on single-process SWE tasks, with frontier models now clustering in the high-70s on SWE-bench Verified. Distributed-system debugging, however, remains an under-explored regime: bugs span processes, nodes, and protocol interactions, with root causes rarely recoverable from source alone and brute-force exploration intractable across non-deterministic interleavings. This leaves two gaps in LLM and agent evaluation: no code-repair benchmark targets distributed-system bugs, and no controlled study isolates how much externally provided debugging context changes agent success on them. We introduce DDBench, a code-repair benchmark of 60 historical bugs mined from 13 open-source distributed systems, partitioned into three difficulty tiers. DDBench evaluates every case under two matched conditions: a symptom-only condition where the agent receives only the bug symptom and repository, and a context-augmented condition where it additionally receives a bounded debugging context (logs, traces, runtime state, and targeted code-investigation notes), isolating the effect of debugging context from model capability. The evaluation of ten LLMs on DDBench reveals several findings. First, distributed debugging exercises a reasoning dimension that single-process benchmarks do not surface: models' pass rates span 61 pp, and pairwise bootstrap separates 9 of 15 top-tier model pairs at p < 0.05 on DDBench's hardest case-set. Second, bounded debugging context lifts aggregate pass rate by +18.1 pp, and the lift is asymmetric: weaker models gain pass rate, while stronger models gain efficiency. Third, debugging context requires careful curation, as even faithful debugging context can sometimes mislead LLMs.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC).
Pagina del lavoro: https://arxiv.org/abs/2608.14863 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T16:29:13.962Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).