跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+86新增论文
+61其中 AI 相关
+14已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 10:40各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 10:53 — 2026-11-16 10:53(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-16 01:34最近发现新增版本:2026-11-16 10:40库内论文最新更新时间:2026-11-13 16:48

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

23,434 已收录论文19,641 AI 相关6,765 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 2 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2611.04829

Geometric Bin Packing Beyond Convexity: Approximation Schemes without Augmentation

Lucas de Oliveira Silva, Elisa Dell'Arriva, Flávio Keidi Miyazawa

原文摘要

We study the geometric bin packing problem for simple polygonal regions, i.e., non-degenerate, connected, rational regions, in the minimum number of unit-square bins, allowing only translations. We even consider packing general non-convex objects, possibly with holes, where we can then pack smaller objects. Previous schemes cover squares (MOR'06), circles and other $L_p$-balls (Algorithmica'16), sufficiently skewed rectangles (Algorithmica'23), and convex fat objects with a constant number of distinct shapes under resource augmentation (arXiv'24, WAOA'23). The result for circles and other $L_p$-balls needs bin augmentation to obtain rational packing realizations. For restricted classes of $L$-shaped polygons, Gerlach et al. (SoCG'26) give constant worst-case guarantees, while for general non-convex objects, bounding-box reductions give just approximation factors that depend on fatness. Against this background, we present a general framework that provides asymptotic polynomial-time approximation schemes (APTAS) for bin packing of any fixed class of simple polygonal regions satisfying just two assumptions. First, covering any object by the grid cells intersecting its interior in any sufficiently fine square grid, relative to the object's bounding box, increases its area by at most a small fraction. Second, the class can be partitioned into a constant number of sequences such that each object in a sequence can be translated to fit inside every preceding object. In particular, certain classes of star-shaped polygons and more general polygonal regions, including some with simple holes, satisfy both assumptions. In addition, our framework does not require a bound on the objects' boundary complexity. We emphasize that our results require no bin augmentation whatsoever and yield explicit, exact rational packings of polynomial encoding length for all input objects.

cs.CG · cs.DS

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.439ACL Anthology · ACL 2026

Benchmarking and Learning Real-World Customer Service Dialogue

Tianhong Gao, Jundong Shen ByteDance Inc., Jiapeng Wang, Bei Shi ByteDance Inc., Ying Ju, Junfeng Yao, Huiyu Yu

原文摘要

Existing benchmarks and training pipelines for industrial intelligent customer service (ICS) remain misaligned with real-world dialogue requirements, overemphasizing verifiable task success while under-measuring subjective service quality and realistic failure modes, leaving a gap between offline gains and deployable dialogue behavior. We close this gap with a benchmark-to-optimization loop: we first introduce OlaBench, an ICS benchmark spanning retrieval-augmented generation, workflow-based systems, and agentic settings, which evaluates service capability, safety, and latency sensitivity; moreover, motivated by OlaBench results showing state-of-the-art LLMs still fall short, we propose OlaMind, which distills reusable reasoning patterns and service strategies from expert dialogues and applies staged exploration–exploitation reinforcement learning with instance-level rubric-aware guidance to improve model capability. OlaMind surpasses GPT-5.2 and Gemini 3 Pro on OlaBench (83.64 vs. 70.58/70.84) and, in online A/B tests, delivers an average +23.67% issue resolution and -6.6% human transfer rate versus the baseline, bridging offline gains to deployment. Together, OlaBench and OlaMind advance ICS systems toward more anthropomorphic, professional, and reliable deployment. The project page and evaluation are available at https://olamind-olabench.github.io.

cs.CL · cs.AI

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表