扩散语言模型的自蒸馏新方法登上ACL 2026，生成效率与质量或迎来新突破。
arXiv:2608.22898v1 Announce Type: new Abstract: Diffusion language models (DLMs) alleviate the inherent latency bottleneck of autoregressive (AR) larg…
解读LLM安全新漏洞：不完整提示即可绕过模型防护，ACL 2026前沿研究揭示越狱攻击新范式。
arXiv:2607.20473v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly released as open-weight models with safeguards against h…
智能体不再依赖自然语言，直接在潜在空间高效沟通，突破传统交互瓶颈。
arXiv:2511.09149v5 Announce Type: replace-cross Abstract: While natural language is the de facto communication medium for LLM-based agents, it present…
用MDL引导规则学习，让语言代理更会挑工具、用工具，ACL 2026长文带你秒懂核心机制。
arXiv:2601.00086v3 Announce Type: replace Abstract: Large language models (LLMs) often struggle to use tools reliably in domain-specific settings, whe…
用进化算法迭代精炼价值，提升大模型解码质量，被ACL 2026接收的前沿研究。
arXiv:2503.02368v4 Announce Type: replace-cross Abstract: While guided decoding, especially value-guided methods, has emerged as a cost-effective alte…
新方法STAPO：选择性轨迹感知策略优化，提升LLM智能体训练效率与性能
arXiv:2607.04963v1 Announce Type: new Abstract: Reinforcement Learning (RL) is the dominant paradigm for training Large Language Model (LLM) agents on…
引入约束感知强化学习，让LLM规划不再“天马行空”，ACL 2026最新研究。
arXiv:2607.04854v1 Announce Type: new Abstract: Despite their strong reasoning capabilities and extensive world knowledge, Large Language Models (LLMs…
评估针对大模型的心理引导技术效果与可信度，为安全可控的AI应用提供新视角。
arXiv:2510.04484v2 Announce Type: replace-cross Abstract: The ability to control LLMs' emulated emotional states and personality traits is an essentia…
美团履约团队ACL 2026前沿技术，揭秘GeoRA与UserLM-R1如何用连续概率流革新推理模型。
美团业务研发平台/履约 AI 算法团队，聚焦构建大模型为基础的 Agent 技术体系，用 AI 赋能美团履约业务， 构建 Agent 自进化的运营系统。在大模型 CPT、Post-training、Agentic RL 以及多模态理解等核心前沿方向持续深耕，已在 ACL、EMNLP 等AI领域的国际…
自动化生成可定制Web环境，为GUI Agent训练提供无限规模、高保真交互场景。
arXiv:2601.04126v3 Announce Type: replace-cross Abstract: GUI agents that interact with graphical interfaces on behalf of users represent a promising …
首个评估大模型逻辑谬误鲁棒性的基准，揭示LLM在诡辩面前的漏洞，被ACL 2026收录。
arXiv:2606.31039v1 Announce Type: new Abstract: Large Language Models (LLMs) exhibit strong semantic capabilities, yet their resilience to manipulativ…
只用推理一致性就能训练强化专家，这项研究为语言模型推理提效打开了新思路。
arXiv:2510.09278v2 Announce Type: replace Abstract: Training expert LLMs in domains with scarce data is difficult, often relying on multiple-choice qu…
教大模型用Prolog做逻辑推理，提升复杂任务准确率，AI工具融合新思路。
arXiv:2512.07407v3 Announce Type: replace Abstract: Language models frequently produce plausible yet incorrect reasoning traces that are difficult to …
探究数据混合与模型架构对非洲语言持续预训练的影响，为低资源语言建模提供前沿实证与设计指南。
arXiv:2601.06395v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly multilingual, yet open models continue to underperfo…
免训练实体识别新方法，先定位再排序，显著提升知识型视觉问答表现
arXiv:2606.23881v1 Announce Type: new Abstract: Knowledge-Based Visual Question Answering (KB-VQA) requires grounding visual queries to external knowl…
AI代理扎堆竟自发分出阶层？看ACL论文揭秘群体情绪如何催生权威等级
arXiv:2606.23764v1 Announce Type: cross Abstract: Fei Xiaotong's Differential Order Pattern characterizes rural society as egocentric and relationally…
大模型批量知识编辑新方法，用正交表示解耦语义纠缠，精准修正知识而不干扰其他能力。
arXiv:2606.22627v1 Announce Type: cross Abstract: Knowledge editing aims to efficiently update factual information in Large Language Models (LLMs) wit…
用动作剪枝替代参数剪枝，LLM搜索不再“又慢又贵”，效率质量双赢的ACL 2026研究。
arXiv:2505.16312v2 Announce Type: replace Abstract: Large Language Models (LLMs) excel at complex reasoning through search algorithms, yet current str…
LLM生成故事的角色多样性研究，ACL 2026论文揭示模型角色生成规律。
arXiv:2606.22454v1 Announce Type: cross Abstract: As LLM-generated text is increasingly used, especially in fictional domains, we explore how much LLM…
新方法量化LLM在上下文学习中的偶然不确定性，提升预测置信度的鲁棒性，已被ACL 2026接收。
arXiv:2606.19353v1 Announce Type: cross Abstract: In-Context Learning (ICL) allows LLMs to adapt to new tasks from a few demonstrations, but its relia…