arXiv AI July 31, 2026 By Zijian Xu, Wenshuo Zhang, Zisen Qin, Rui Sheng, Yushi Sun, Huamin Qu, Chuhan Shi

Fewer Clarifications, Better Code: Benchmarking Cross-Session Personalized Ambiguity Adaptation in Coding Assistants

arXiv:2607. 26611v1 Announce Type: new Abstract: AI-assisted coding increasingly translates informal user intent into executable software, yet coding requests often contain ambiguities that recur in user-specific ways across tasks and sessions.

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 AI.

arXiv AI

Jun 9

Lost in the Flow with Code Talkers: Unveiling the Instruction-Tuning Tax of Large Language Models in Code Tasks

arXiv:2606. 08676v1 Announce Type: cross Abstract: AI coding assistants have significantly improved developer productivity by automatically suggesting code that aligns with user intent, and many of these tools are now integrated directly into Integrated Development Environments (IDEs).

By Shi Ying Chang, Chiok Yew Ho, Yichen Li, Yintong Huo

llms fine-tuning

arXiv AI

4d ago

ProCompNav: Proactive Instance Navigation with Comparative Judgment for Ambiguous User Queries

arXiv:2605.06223v4 Announce Type: replace Abstract: Natural-language instance navigation becomes challenging when the initial user request does not uniquely specify the target instance. A practical a...

By Junhyuk Kwon, Seungjoon Lee, Hyejin Park, Kyle Min, Jungseul Ok

agents benchmarks

arXiv AI

Aug 12

Do Personalized Skills Help Coding Agents? An Empirical Study of Developer Interaction Histories

arXiv:2608. 10319v1 Announce Type: cross Abstract: Large language model (LLM)-powered agents have rapidly evolved from code-completion tools into solvers of complex software engineering tasks.

By Shuyan Huang, Kai Du, Andrew Lan

llms agents

arXiv AI

Jul 17

Automatically Evolving Prompt Guidelines for Task-Specific Optimization

arXiv:2607. 14105v1 Announce Type: cross Abstract: For Large Language Models to reliably answer user queries, users must clearly specify requirements, context, and constraints.

By Cedric Richter, Salah Ghamizi, Mike Papadakis

llms nlp benchmarks

arXiv AI

Jul 3

Leveraging Metamemory Agent for Enhanced Data-Free Code Generation in Large Language Models

arXiv:2501. 07892v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown strong performance in automated code generation, with few-shot prompting widely used for its simplicity and effectiveness.

By Shengsheng Zhou, Shuai Wang, Liang Ding, Yibing Zhan, Yong Luo, Zheng He, Fu Lin, Dapeng Tao

llms agents benchmarks

arXiv Machine Learning

Aug 31

RealSWE: A Compositional Evaluation of Coding Agents under Realistic User Requests

arXiv:2608.27831v1 Announce Type: cross Abstract: Coding agents are now commonly evaluated on the SWE-bench family of benchmarks, whose tasks are built from curated GitHub issues--long, structured, a...

By Gyuhyeong Kim, Hyojung Gwon, Jeonghyeon Kim, Kyuhong Shim, Sunjae Lee

llms agents benchmarks

One email a morning, machine-written

Related stories

Lost in the Flow with Code Talkers: Unveiling the Instruction-Tuning Tax of Large Language Models in Code Tasks

ProCompNav: Proactive Instance Navigation with Comparative Judgment for Ambiguous User Queries

Do Personalized Skills Help Coding Agents? An Empirical Study of Developer Interaction Histories

Automatically Evolving Prompt Guidelines for Task-Specific Optimization

Leveraging Metamemory Agent for Enhanced Data-Free Code Generation in Large Language Models

RealSWE: A Compositional Evaluation of Coding Agents under Realistic User Requests