arXiv AI October 5, 2026 By Zheng Fang, Yihong Dong, Lili Mou, Dongming Jin, Zhi Jin, Ge Li

IntentCoding: Amplifying User Intent in Code Generation

IntentCoding is a decoding strategy that amplifies user intent in large language model code generation by masking the intent and applying a multi‑strength ensemble mechanism. It is model‑agnostic, requires no extra training, and integrates with existing decoding procedures. Experiments on the new CodeConstraints benchmark and other datasets show significant improvements in constraint satisfaction and functional correctness, with up to 71.0% relative gains on CodeConstraints and 29.3% on HumanEval and LiveCodeBench compared to greedy decoding.

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 Computation and Language

Aug 24

Intent Engine: Natural-Language Intent Translation for Intent-Driven Orchestration in the Compute Continuum

Intent Engine is a natural‑language intent translation architecture that converts user intents into validated Service‑level Objectives (SLOs) for compute‑continuum microservice placement. It combines schema‑constrained extraction, retrieval‑grounded value construction from monitored infrastructure, and validation against supported constraints to produce reliable SLO artifacts. In evaluations on a 716‑record dataset, Intent Engine outperformed prompting baselines and a rule‑based parser, achieving a 0.941 total F1 score with GPT‑4.1 mini and reducing downstream placement failures from 30.8% to 2.1%.

By Koushikur Islam, Rodrigo N. Calheiros

llms agents safety

arXiv AI

Aug 3

WebCoderBench: Benchmarking Web Application Generation with Comprehensive and Interpretable Evaluation Metrics

arXiv:2601. 02430v3 Announce Type: replace-cross Abstract: Web applications (web apps) have become a key arena for large language models (LLMs) to demonstrate their code generation capabilities and commercial potential.

By Chenxu Liu, Yingjie Fu, Wei Yang, Ying Zhang, Tao Xie

llms agents benchmarks

arXiv AI

Jul 31

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.

By Zijian Xu, Wenshuo Zhang, Zisen Qin, Rui Sheng, Yushi Sun, Huamin Qu, Chuhan Shi

llms benchmarks

arXiv Machine Learning

Jul 31

Selecting Open-Weight Language Models for Zero-Shot Intent Classification: A Systematic Evaluation of 41 Models

arXiv:2607. 27421v1 Announce Type: cross Abstract: Intent classification is a core component of task-oriented dialogue systems, yet practitioners have limited systematic guidance for selecting deployable open-weight language models under compute, latency, and robustness constraints.

By Parishruthi Ganesh, Gerry Dozier, Cheryl Seals

llms fine-tuning benchmarks

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 Machine Learning

Sep 30

Koa-action: Fast and Consistent Structured Decision Making with Generative LLMs

arXiv:2609.36115v1 Announce Type: new Abstract: Industry applications often demand low-latency classification, yet current large language model (LLM) approaches remain poorly suited for latency-criti...

By Shenghong Dai, Shiva Kumar Pentyala, Yingchi Liu, Shubham Mehrotra, Suman Banerjee, James Zhu, Bin Bi, Sitaram Asur, Phil Mui

llms fine-tuning multimodal benchmarks

One email a morning, machine-written

Related stories

Intent Engine: Natural-Language Intent Translation for Intent-Driven Orchestration in the Compute Continuum

WebCoderBench: Benchmarking Web Application Generation with Comprehensive and Interpretable Evaluation Metrics

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

Selecting Open-Weight Language Models for Zero-Shot Intent Classification: A Systematic Evaluation of 41 Models

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

Koa-action: Fast and Consistent Structured Decision Making with Generative LLMs