LLM智能体在预算约束与优惠券组合购物中表现如何？全新基准ComboShoppingBench给出量化答案
arXiv:2608.09282v1 Announce Type: new Abstract: Real-world shopping often requires constructing a basket of complementary items rather than retrieving…
评估LLM代理在预算约束下的经济决策，揭示资源效率与任务完成度的平衡新基准。
arXiv:2608.05519v1 Announce Type: new Abstract: Agent benchmarks usually measure task completion and treat resource use as an auxiliary statistic. In …
新论文提出WISERouter，在预算约束下智能路由LLM请求，兼顾成本与性能。
arXiv:2607.23765v1 Announce Type: new Abstract: Large language models (LLMs) achieve impressive performance across multiple domains, but using the mos…
预算受限下如何诊断并修复RAG事实错误？新方法给出高效方案，值得关注。
arXiv:2606.29377v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) improves the factuality of large language models by grounding res…
预算有限也要公平？这篇论文提出FairTutor，为AI辅导场景设计公平感知的大模型路由策略。
arXiv:2606.20713v1 Announce Type: new Abstract: Generative AI tutors provide real-time, personalized learning support, but also create a new education…
扩散模型推理还能更省？预算约束下的步骤级缓存策略，为生成式AI降本增效提供新思路。
arXiv:2606.13496v1 Announce Type: new Abstract: Step-level caching accelerates diffusion models by exploiting temporal redundancy across denoising ste…
预算受限下如何高效筛选微预训练配方？分阶段因子筛选方法或可稳定识别早期效应结构
arXiv:2606.05186v1 Announce Type: cross Abstract: Budget-constrained micro-pretraining often requires triaging many candidate recipes on a shared acce…
首个将物理模拟工具成本纳入LLM评估的基准，让科学自动化更贴近现实预算约束。
arXiv:2603.20253v2 Announce Type: replace-cross Abstract: Evaluating LLM agents for scientific tasks has focused on token costs while ignoring tool-us…