The paper proposes an agentic framework for multimodal emotion reasoning that uses frozen models to avoid costly instruction tuning. It employs modality‑specific perception agents, an integration agent, and an MLLM critic to generate emotion predictions with evidence citations, followed by an evidence‑grounded verification stage that identifies errors and applies targeted prompt patches without updating model weights. On the MER2025 dataset, this approach improves F‑score across several large language‑vision models, outperforming static pipelines and matching or exceeding reflection baselines.
By Elyas Rashno, Farhana Zulkernine
The paper introduces VERID, a semantic digital twin for laboratory workcells that bridges AI agent reasoning with the physical realities of wet labs. VERID offers queryable introspection, time‑compressed simulation, trace persistence, and a safe execution framework, enabling agents to detect errors, recover mid‑run, and validate protocols in silico. Three case studies with dye and water mixtures demonstrate VERID’s ability to pre‑emptively catch critical errors, recover from failures, and provide structured multimodal data for downstream analysis and agent training.
By Yves Delley, John Coller, Zachary Cutts, Alexander Daryin, Mathias Bellaiche, Jun W. Kim, Oscar Donosa, Srinidhi B. Seshadri, Tanner Clary, Sandy Klemm, Avinatan Hassidim, Yossi Matias, Pooja Rao, Petar Sirkovic, Annalisa Pawlosky
The paper introduces SCENE, a bi-level multi-agent framework that transforms broad biomedical knowledge into scenario‑grounded propositions. SCENE operates by iteratively converting general knowledge into dataset‑specific search directions and then optimizing for propositions that balance evidential strength and data support. The method is evaluated on clinical trial subgroups and LINCS L1000 perturbation studies, outperforming baselines and yielding traceable, inspectable hypotheses.
By Qingyuan Zeng, Ziyang Chen, Pengxiang Cai, Zixin Guan, Anglin Liu, Lang Qin, Xinyao Lai, Jintai Chen
arXiv:2610.31840v1 Announce Type: new
Abstract: Tool-calling agents are mostly optimized for accuracy; in deployment, however, their growing cost is latency: every tool call is decoded autoregressive...
By Zihe Song, Wenting Zhao, Ye Liu, Yuanjie Zhu, Ke Xu, Shanghao Li, Philip S. Yu
arXiv:2610.32002v1 Announce Type: new
Abstract: The rapid growth of microdramas has increased demand for high-quality script production. Long-form microdrama script generation with LLMs requires both...
By Siyang He, Qiqi Wang, Fan Liu, Yuncheng Huang, Pengfei Xu, Xi Chen, Ziwei He, Xipeng Qiu
arXiv:2610.32107v1 Announce Type: new
Abstract: Participating in a conversation involves not only deciding what to say but also whether to speak at all. This judgment carries even greater significanc...
By Yoshiki Tanaka, Shuya Uchiyama, Daichi Hamaguchi, Michimasa Inaba
arXiv:2610.32415v1 Announce Type: new
Abstract: LLM-based annotation has advanced rapidly, yet existing benchmarks remain misaligned with real-world practice. Actual annotation often involves lengthy...
By Xiaopeng Ke, Zhixin Wang, Xuebo Liu, Xinyu Ma, Xing Zheng, Bowen Song, Weiqiang Wang, Min Zhang
arXiv:2610.32575v1 Announce Type: new
Abstract: Large language models and agents have shown significant power in advanced physical research. In this paper, We introduce PHYRD, a living benchmark for...
By Qituan Zhang, Guo Chen, Linfeng Zhang, Wenlong Zhang
arXiv:2610.32871v1 Announce Type: new
Abstract: Latent communication requires both an effective continuous reasoning process and an interface through which an external model can leverage its intermed...
By Xiangwei Wang, Wei Wang, Sachith Seneviratne, Ken Chen, Yu Xia, Peng Wang, Saman Halgamuge
arXiv:2607.25202v2 Announce Type: replace
Abstract: Conversational entrainment is well-studied in monolingual and written contexts, but remains underexplored in spoken code-switching (CSW). We presen...
By Debasmita Bhattacharya, Siying Ding, Alayna Nguyen, Julia Hirschberg
arXiv:2602.01331v2 Announce Type: replace-cross
Abstract: Contemporary large language model (LLM)-based multi-agent systems exhibit systematic advantages in deep research tasks, which emphasize itera...
By Mingju Chen, Guibin Zhang, Heng Chang, Xiao Wang, Shiji Zhou
arXiv:2606.21037v3 Announce Type: replace-cross
Abstract: The empirical foundation of cyber deception relies on human-centered hypotheses, but the rapid emergence of autonomous, AI-enabled attackers...
By Kerri Prinos, Lilianne Brush, Cameron Denton
arXiv:2610.32230v1 Announce Type: new
Abstract: Modern autonomous driving systems widely adopt multi-view Bird's-Eye-View (BEV) based 3D perception models due to their superior performance. Despite t...
By Linye Lyu, Jiawei Zhou, Daojing He, Yu Li
arXiv:2610.32848v1 Announce Type: new
Abstract: Non-invasive camera-trap monitoring of endangered wildlife requires open-set individual identification---grouping field images into identities without...
By Yichun Peng, Yansong Li, Jin Hou, Qi Song, Xi Guo, Ning Zhang, Degang Wei, Huang Yang, Yu Guan, Jianping Ge, Lei Bao, Tianming Wang
arXiv:2503.10212v3 Announce Type: replace
Abstract: Analyzing animal behavior is crucial in neuroscience, yet deciphering its intricate dynamics remains challenging. Traditional machine vision approa...
By Teng Xu, Taotao Zhou, Youjia Wang, Peng Yang, Simin Tang, Kuixiang Shao, Zifeng Tang, Yifei Liu, Xinyuan Chen, Yihan Liu, Zhengning Xu, Boyang Xia, Hongshuang Wang, Xiaohui Wang, Huoqing Luo, Jingya Wang, Ji Hu, Jingyi Yu
arXiv:2610.25068v2 Announce Type: replace-cross
Abstract: Resource-constrained robots and autonomous vehicles need scene memories that localize a camera and render nearby views without a desktop GPU....
By Haohua Que, Mingkai Liu, Tianle Zhu, Handong Yao
The paper compares two approaches to pragmatic intent recognition in human‑robot interaction: FISER, which uses structured symbolic reasoning, and CEMIR, which enriches textual prompts with synthetic narratives and images. Experiments across four large language models on the HandMeThat v2 benchmark show no statistically significant performance difference between the two methods, regardless of model size or ambiguity difficulty. The results indicate that when task constraints are already present in the text, multimodal enrichment offers no measurable advantage over structured reasoning.
By Ziya Hosseynzadeh, Farjad Fallah, Farnoosh Fallah, Soroush Gooran, Mohammad Amanloo, Hossein Sameti
The paper introduces an offline evaluation harness that remains reproducible even as live enterprise data changes, allowing for on-demand regeneration when benchmarks become stale. This harness is used as a fitness function for GEPA-based prompt compression, with a correctness gate to prevent reward hacking. In a production merchant-facing agent, the method reduces the prompt size by 3.5‑7.6% while maintaining or improving task correctness across multiple model families.
By Prabal Vashisht, Zheng Hu, Ying Yang
CRM‑Agent‑Bench is a benchmark that evaluates language agents in customer‑relationship‑management settings by testing 555 stateful, multi‑turn tasks across nine business domains. Each task includes an executable contract with checks on actions, arguments, order, responses, target state, and protected state, and success requires meeting all these checks. The benchmark reports coverage, latency, and cost, showing that evaluated systems achieve 64.32%–83.60% strict success while varying in cost and domain reliability.
By Monojit Banerjee, Zhujun Lan, Defu Cao
ProfileSim is a profile‑driven user simulation framework designed for financial marketing outbound calls. It jointly models user demographics, Big Five personality traits, and business intents reverse‑engineered from real call logs, allowing fine‑grained control over simulated behavior. The system is fine‑tuned on real voice dialogue data and further refined with Group Relative Policy Optimization using hierarchical rewards, achieving high colloquial naturalness, strong user profile adherence, and low agent scores on long‑tail intents while producing shorter user utterances.
By Juan Li, Fangshu Chang, Xinyi Jiang, Ling Huang, Yunzhang Chen