VibeServe demonstrates that AI agents can synthesize bespoke LLM serving systems end-to-end, remaining competitive with vLLM in standard settings while outperforming it in six non-standard scenarios involving unusual models, workloads, or hardware.
Swe-perf: Can language models optimize code performance on real-world repositories?
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
abstract
Code performance optimization is paramount in real-world software engineering and critical for production-level systems. While Large Language Models (LLMs) have demonstrated impressive capabilities in code generation and bug fixing, their proficiency in enhancing code performance at the repository level remains largely unexplored. To address this gap, we introduce SWE-Perf, the first benchmark specifically designed to systematically evaluate LLMs on code performance optimization tasks within authentic repository contexts. SWE-Perf comprises 140 carefully curated instances, each derived from performance-improving pull requests from popular GitHub repositories. Each benchmark instance includes the relevant codebase, target functions, performance-related tests, expert-authored patches, and executable environments. Through a comprehensive evaluation of representative methods that span file-level and repo-level approaches (e.g., Agentless and OpenHands), we reveal a substantial capability gap between existing LLMs and expert-level optimization performance, highlighting critical research opportunities in this emerging field.
citation-role summary
background 3
method 1
citation-polarity summary
years
2026 13representative citing papers
JETO-Mine and JETO-Bench provide a configurable, Docker-based pipeline and dataset of 91 verified Java execution-time improvement patches, on which OpenHands fixes 13 of 91 issues (14.3%).
SaaSBench introduces a heterogeneous benchmark for enterprise SaaS engineering and shows that state-of-the-art coding agents fail over 95% of the time before reaching deep business logic due to setup and integration problems.
BootstrapAgent distills repository bootstrapping heuristics into a persistent .bootstrap contract via multi-agent evidence extraction, Docker verification, and trace-driven repair, reporting 92.9% success and efficiency gains on three benchmarks.
Phoenix-bench shows agentic AI systems lose 37-58% resolved rate when moving from SWE-bench Verified to hardware tasks because bugs spread across parallel modules via signal flow, with testbench feedback lifting performance by 42-45% while file-level oracles add only 1.4%.
CppPerf-Mine produces CppPerf-DB, a benchmark of 347 real-world performance-improving C++ patches (39% multi-file) from 42 repositories to evaluate repository-level repair tools.
PlayCoder raises the rate of LLM-generated GUI apps that can be played end-to-end without logic errors from near zero to 20.3% Play@3 by adding repository-aware generation, agent-driven testing, and iterative repair.
Re-evaluating four LLM code-efficiency benchmarks with 30-run statistical testing shows 93.89% of 'performant' implementations are indistinguishable from baselines; a multi-agent test-generation framework reveals hidden significant improvements in ~24% of previously non-significant tasks.
Coding-agent performance is workload- and framework-dependent, and raw speedup is an unsafe score because agents exploit benchmark-specific shortcuts.
SWE Atlas is a benchmark suite for coding agents that evaluates Codebase Q&A, Test Writing, and Refactoring using comprehensive protocols assessing both functional correctness and software engineering quality.
PlayCoder combines a repository-aware coding agent with a vision-based GUI testing agent and an automated program repair loop to detect and fix silent logic errors in LLM-generated interactive application code.
LLM agents resolve fewer than half of issues while satisfying design constraints despite passing tests, as shown by a benchmark of 495 issues and 1787 constraints from six repositories.
citing papers explorer
-
VibeServe: Can AI Agents Build Bespoke LLM Serving Systems?
VibeServe demonstrates that AI agents can synthesize bespoke LLM serving systems end-to-end, remaining competitive with vLLM in standard settings while outperforming it in six non-standard scenarios involving unusual models, workloads, or hardware.
-
JETO-Bench: A Reproducible Benchmark for Execution Time Improvement Patches in Java
JETO-Mine and JETO-Bench provide a configurable, Docker-based pipeline and dataset of 91 verified Java execution-time improvement patches, on which OpenHands fixes 13 of 91 issues (14.3%).
-
SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering
SaaSBench introduces a heterogeneous benchmark for enterprise SaaS engineering and shows that state-of-the-art coding agents fail over 95% of the time before reaching deep business logic due to setup and integration problems.
-
BootstrapAgent: Distilling Repository Setup into Reusable Agent Knowledge
BootstrapAgent distills repository bootstrapping heuristics into a persistent .bootstrap contract via multi-agent evidence extraction, Docker verification, and trace-driven repair, reporting 92.9% success and efficiency gains on three benchmarks.
-
Is Agentic AI Ready for Real-World Hardware Engineering? A Deep Dive with Phoenix-bench
Phoenix-bench shows agentic AI systems lose 37-58% resolved rate when moving from SWE-bench Verified to hardware tasks because bugs spread across parallel modules via signal flow, with testbench feedback lifting performance by 42-45% while file-level oracles add only 1.4%.
-
CppPerf: An Automated Pipeline and Dataset for Performance-Improving C++ Commits
CppPerf-Mine produces CppPerf-DB, a benchmark of 347 real-world performance-improving C++ patches (39% multi-file) from 42 repositories to evaluate repository-level repair tools.
-
PlayCoder: Making LLM-Generated GUI Code Playable
PlayCoder raises the rate of LLM-generated GUI apps that can be played end-to-end without logic errors from near zero to 20.3% Play@3 by adding repository-aware generation, agent-driven testing, and iterative repair.
-
Rethinking Code Performance Benchmarks for LLMs
Re-evaluating four LLM code-efficiency benchmarks with 30-run statistical testing shows 93.89% of 'performant' implementations are indistinguishable from baselines; a multi-agent test-generation framework reveals hidden significant improvements in ~24% of previously non-significant tasks.
-
PERFOPT-Bench: Evaluating Coding Agents on Software Performance Optimization
Coding-agent performance is workload- and framework-dependent, and raw speedup is an unsafe score because agents exploit benchmark-specific shortcuts.
-
SWE Atlas: Benchmarking Coding Agents Beyond Issue Resolution
SWE Atlas is a benchmark suite for coding agents that evaluates Codebase Q&A, Test Writing, and Refactoring using comprehensive protocols assessing both functional correctness and software engineering quality.
-
CityRAG: Stepping Into a City via Spatially-Grounded Video Generation
PlayCoder combines a repository-aware coding agent with a vision-based GUI testing agent and an automated program repair loop to detect and fix silent logic errors in LLM-generated interactive application code.
-
Does Pass Rate Tell the Whole Story? Evaluating Design Constraint Compliance in LLM-based Issue Resolution
LLM agents resolve fewer than half of issues while satisfying design constraints despite passing tests, as shown by a benchmark of 495 issues and 1787 constraints from six repositories.
- Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy Search