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…
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…
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…
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…
多语言数学推理中，LLM参数共享还是分离更优？这项ACL 2026研究给出了实验性答案。
arXiv:2606.18453v1 Announce Type: new Abstract: Large language models (LLMs) exhibit substantial cross-lingual variation in mathematical reasoning per…
多语言机器生成文本的作者归属研究，ACL 2026 主会论文，为检测 AI 文本提供新思路。
arXiv:2508.01656v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) have reached human-like fluency and coherence, distinguishin…
新基准WildIFEval带你从实验室走进真实世界的指令跟随能力评估
arXiv:2503.06573v3 Announce Type: replace-cross Abstract: Recent LLMs have shown remarkable success in following user instructions, yet handling instr…
用小语言模型低成本搞定生物医学声明验证，揭秘结构化数据集捷径与跨域泛化新发现。
arXiv:2606.12854v1 Announce Type: new Abstract: Large Language Models such as GPT-4o and GPT-5 achieve strong zero-shot performance on biomedical clai…
ACL 2026收录论文：系统提出语言模型在开放任务中创造力的自动化评估方法，填补量化空白。
arXiv:2606.11762v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved remarkable progress in language understanding, reasoning,…
人机协作写作竟藏越狱风险？新基准揭示大模型安全新盲区
arXiv:2604.19274v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used as co-authors in collaborative writing, where u…
基于Plutchik情感模型的价值规划方法，实现高表现力流式情感语音合成，被ACL 2026录用。
arXiv:2606.09837v1 Announce Type: cross Abstract: Emotional interaction is increasingly crucial for conversational AI, yet current systems lack a self…
大规模多语言联合分词与标注方法，ACL 2026长文带来NLP新突破。
arXiv:2601.10925v3 Announce Type: replace Abstract: Automated interlinear gloss prediction with neural networks is a promising approach to accelerate …
ACL 2026论文：用轻量级专家集成方法，解决大模型不可验证约束对齐难题，提升安全性与可控性。
arXiv:2606.07520v1 Announce Type: cross Abstract: Instruction Following (IF) is a core capability of LLMs, requiring strict adherence to diverse const…
提出专家评分标准解决RLVR中复杂约束问题，为强化学习奖励设计提供新范式
arXiv:2606.09118v1 Announce Type: new Abstract: As LLM capabilities advance rapidly, the evaluation methods used to assess them increasingly lag behin…
多模态MoE推理效率新突破：模态感知的容量扩展策略，实现计算资源动态分配。
arXiv:2605.05225v3 Announce Type: replace-cross Abstract: Mixture-of-Experts Multimodal Large Language Models (MoE MLLMs) suffer from a significant ef…