arXiv Computation and Language By Xiao Zhang, Qumeng Sun, Jihao Li, Yiming Ren, Xiang Liu, Haoyang Zhang, Junjie Wang

LongWoF-Bench: Evaluating EvoMap Genes for Verifiable Long-Workflow Tasks

Read the original on arXiv Computation and Language →

LongWoF-Bench is a new benchmark of 778 machine‑verifiable long‑workflow tasks spanning code generation, agent‑environment synthesis, mathematical reasoning, and rule following. The study shows that EvoMap Genes—structured representations of verifier‑confirmed execution trajectories—outperform the Skill baseline by 8.7–15.5 percentage points across seven models, and for Claude Opus they enable 39 additional task completions while cutting token consumption by 9.9%. The results demonstrate that verified execution experience can be externalized and reused, improving long‑workflow completion without repeatedly discovering new strategies.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI
Jun 2

BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution

arXiv:2606. 01286v1 Announce Type: cross Abstract: The rapid progress of frontier large language models has led to widespread benchmark saturation, limiting the ability of existing datasets to differentiate model capabilities or provide useful training signal.

By Yangzhen Wu, Aaron J. Li, Wenjie Ma, Li Cao, Ziheng Zhou, Mert Cemri, Shu Liu, Yuran Xiu, Chenxiao Yan, Haikun Zhao, Bin Yu, Ion Stoica, Dawn Song
arXiv AI
Sep 4

Evolving Excellence: Automated Optimization of LLM-based Agents

The paper introduces ARTEMIS, a no-code evolutionary optimization platform that automatically tunes large language model (LLM) agents by jointly optimizing prompts, tool descriptions, and parameters using semantically-aware genetic operators. Starting from a benchmark script and natural language goals, ARTEMIS discovers configurable components, extracts performance signals from execution logs, and evolves configurations without architectural changes. Experiments on four agent systems show significant gains: a 13.6% increase in acceptance rate for the ALE Agent, a 10.1% performance boost for the Mini‑SWE Agent, a 36.9% token‑reduction for the CrewAI Agent, and a 22% accuracy improvement for the MathTales‑Teacher Agent using a smaller open‑source model.

By Paul Brookes, Vardan Voskanyan, Rafail Giavrimis, Matthew Truscott, Mina Ilieva, Chrystalla Pavlou, Alexandru Staicu, Manal Adham, Will Evers- Hood, Jingzhi Gong, Kejia Zhang, Matvey Fedoseev, Vishal Sharma, Roman Bauer, Zheng Wang, Hema Nair, Wei Jie, Tianhua Xu, Aurora Constantin, Leslie Kanthan, Michail Basios
arXiv AI
Jun 30

SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?

arXiv:2511. 06090v3 Announce Type: replace-cross Abstract: Optimizing the performance of large-scale software repositories demands expertise in code reasoning and software engineering (SWE) to reduce runtime while preserving program correctness.

By Jeffrey Jian Ma, Milad Hashemi, Amir Yazdanbakhsh, Kevin Swersky, Ofir Press, Enhui Li, Vijay Janapa Reddi, Parthasarathy Ranganathan