Take It From Here: Evaluating Coding Agents On Project Takeover
arXiv:2611.07307v1 Announce Type: new Abstract: Coding agents increasingly collaborate on long-term projects. When taking over a project, they need to recover c…
EnglisharXiv cs.SE
最新资讯
言栖资讯收录 139053 篇 AI、开发与建站文章（English），按发布时间排序，支持搜索与按语言筛选。
How Should Agents See Code? Rethinking Code Representations for Agentic Software Engineering
arXiv:2611.07286v1 Announce Type: new Abstract: LLM agents are increasingly used for repository-level software engineering tasks. However, most agents still acc…
EnglisharXiv cs.SE
SeVerus: Context-Aware, Gamified Benchmarking for Rust Verification
arXiv:2611.07194v1 Announce Type: new Abstract: Coding agents achieve high success rates on existing benchmarks for Verus, a verifier for Rust programs. These b…
EnglisharXiv cs.SE
Multi-step SWE: Can Coding Agents Keep Building on Their Own Code Over Long Horizons?
arXiv:2611.07166v1 Announce Type: new Abstract: Developers rarely give a coding agent a single request: they ask it to build a component and then to extend, upg…
EnglisharXiv cs.SE
Automatic Assistance to Reduce Information Overload during Software Issue Report Understanding
arXiv:2611.07109v1 Announce Type: new Abstract: Modern issue tracking systems are used to log an issue and track it from its inception to closure. Issue reports…
EnglisharXiv cs.SE
An LLM-Orchestrated Neuro-Symbolic Framework for Verifying Diagnostic Signal Reachability in Electronic Systems
arXiv:2611.07040v1 Announce Type: new Abstract: Diagnostic Signal Reachability (DSR) captures whether board-level health signals are observable by management co…
EnglisharXiv cs.SE
Call-Level Revision Contracts for LLM-Authored Workflows
arXiv:2611.06967v1 Announce Type: new Abstract: Durable execution engines replay a recorded history and do not compare activity payloads. When a model repairs a…
EnglisharXiv cs.SE
When Can Self-Play Fix a False Belief? Answer Keys, Pass Bands and Replacement Rules in an Execution-Grounded Loop
arXiv:2611.06965v1 Announce Type: new Abstract: Self-play loops in which a model writes tasks, derives an answer key and trains on its own matching solutions ar…
EnglisharXiv cs.SE
Operationalizing Responsible AI in MLOps and ML Production: A Systematic Literature Review
arXiv:2611.06961v1 Announce Type: new Abstract: Artificial intelligence (AI)-enabled systems are increasingly deployed in operational environments where machine…
EnglisharXiv cs.SE
KG-AST for Cheaper CI/CD: Budgeted Test Selection and AI Bug Review
arXiv:2611.06950v1 Announce Type: new Abstract: Continuous integration and AI-assisted review spend the same budget on every commit, although few commits introd…
EnglisharXiv cs.SE
When Does Combining Software-Effort Estimates Help? Evidence from Four Public Project Datasets
arXiv:2611.06948v1 Announce Type: new Abstract: Combining estimates can reduce individual prediction errors, but an ensemble may also dilute an unusually accura…
EnglisharXiv cs.SE
How Python Audio Libraries Change Across Releases: Module Structure and Documentation
arXiv:2611.06947v1 Announce Type: new Abstract: Developers who upgrade a Python audio library need to know what changed in the code they import and whether the …
EnglisharXiv cs.SE
Beyond the Agent Harness: Boundary Criteria for Software-Factory Orchestration - A Single-Operator Case Study
arXiv:2611.06946v1 Announce Type: new Abstract: Several recent systems add a layer above the coding-agent harness that organises many agent runs into continuous…
EnglisharXiv cs.SE
A Multi-Modal Robotic Framework for Physical GUI Interaction Testing
arXiv:2611.06939v1 Announce Type: new Abstract: Automated testing of mobile applications remains challenging when realistic user interactions must be reproduced…
EnglisharXiv cs.SE
Towards Comprehensive Mobile Application Testing for User-centric Feature Coverage via Simulating Real-World Users with Personas
arXiv:2611.06922v1 Announce Type: new Abstract: LLM agents are increasingly used for black-box mobile application testing, where the ultimate goal is the compre…
EnglisharXiv cs.SE
TimeArch: A Multi-Agent Approach for Software Architecture Design
arXiv:2611.06921v1 Announce Type: new Abstract: Generative AI is making software implementation faster, but not necessarily better architected. Most current Gen…
EnglisharXiv cs.SE
Random Centres and the $\varepsilon$-Dependence of Constant-Round Planar Domination
arXiv:2610.38020v2 Announce Type: replace Abstract: It was recently shown (arXiv:2610.09618) that the infimum of the approximation ratios of deterministic const…
EnglisharXiv cs.DC
Lantern: Finding Committable Transactions via Back-Propagation on DAGs
arXiv:2609.03315v2 Announce Type: replace Abstract: Existing concurrency control protocols either introduce nondeterminism, resulting in a serial execution-repl…
EnglisharXiv cs.DC
Twig: Parallel and Memory-Efficient Tree Speculative Decoding for Hybrid-Attention LLMs
arXiv:2608.01651v2 Announce Type: replace Abstract: Emerging LLMs increasingly interleave full attention with recurrent linear attention to reduce long-context …
EnglisharXiv cs.DC
Wave-Based Dispatch for Circuit Cutting in Hybrid HPC-Quantum Systems
arXiv:2604.15279v2 Announce Type: replace Abstract: Hybrid High-performance Computing (HPC)-quantum workloads based on circuit cutting decompose large quantum c…
EnglisharXiv cs.DC