paper-with-me

홈 › Papers

BUILD-AND-FIND: An Effort-Aware Protocol for Evaluating Agent-Managed Codebases

2026-05-07 · Jhen-Ke Lin arxiv

Most coding-agent benchmarks ask whether generated code behaves correctly. That remains essential, but repository-level engineering is increasingly agent-managed: one agent writes a repository, and later agents inspect, audit, or extend it as working context. In that setting, a generated repository is not only an answer to a task but also a communication artifact for future work. Even when strong agents nearly satisfy the visible behavioral objective, repositories can differ in how clearly they expose the intended behavior and design choices behind that behavior. We introduce BUILD-AND-FIND, a protocol for evaluating whether downstream agents can recover those intended choices from generated repositories, and how much inspection that recovery requires. For each task, a builder sees a hidden repository specification and creates a codebase; a finder sees only the codebase and a specification-traced multiple-choice question bank. The protocol separates behavioral correctness from artifact-side recovery and reports recovery accuracy, repeatability, implementation coverage, and inspection effort. Accuracy and stability act as gates: effort is interpreted only when recovery succeeds reliably. Among artifacts from which the same intent can be recovered, lower effort by the same finder suggests that the artifact makes that intent easier to locate. Question-only and spec-only controls quantify generic priors and specification access, while audits separate omitted claims from finder failures and check whether correct answers cite artifact evidence. In the released high-prior task pack, recovery accuracy is near saturation, so inspection effort and finder-specific effects provide the main panel-local comparison.

📄 PDF Abstract BibTeX arXiv:2605.06136

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Model Context Protocols in Adaptive Transport Systems: A Survey

2025-08-26 · Gaurab Chhetri, Shriyank Somvanshi, Md Monzurul Islam, Shamyo Brotee 외 arxiv

The rapid expansion of interconnected devices, autonomous systems, and AI applications has created severe fragmentation in adaptive transport systems, where diverse protocols and context sources remain isolated. This sur…

Decision Making

CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs

2026-06-09 · Joachim Schaeffer, Thomas Jiralerspong, Alexander Panfilov, Guillaume Lajoie 외 arxiv

AI control protocols oversee untrusted models by monitoring their actions and modifying potentially unsafe steps, often using a trusted model. This partially tampers with the untrusted model's trajectory. If the trusted …

Binary Classification

CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation

2025-05-30 · Emilio Villa-Cueva, Sholpan Bolatzhanova, Diana Turmakhan, Kareem Elzeky 외

Cultural content poses challenges for machine translation systems due to the differences in conceptualizations between cultures, where language alone may fail to convey sufficient context to capture region-specific meani…

BenchmarkingMachine TranslationMultimodal Machine TranslationTranslation

Dynamically Allocating Evaluation Effort for Model Ranking

2026-08-04 · Vilém Zouhar, Julia Kreutzer, Alon Lavie, Tom Kocmi 외 arxiv

While human evaluation is the gold standard in many NLP tasks, it suffers from prohibitive costs and poor scalability. When identifying top-performing models, typical evaluation protocols waste effort by exhaustively eva…

Protocol-Aware Tokenization and Architecture Co-Design for Wireless Packet Foundation Models

2026-05-14 · Swadhin Pradhan, Shazal Irshad, Jerome Henry arxiv

What matters more for building foundation models for wireless packet traces: the tokenizer or the architecture or both? To answer this question, we build on PLUME Anonymous [2026], which introduced protocol-aware tokeniz…