The paper presents an AI‑powered triaging agent for banks that uses large language models to conduct multi‑turn conversations, ask relevant questions, and classify customer cases for accurate routing to specialist teams. The system is integrated with policy, safety guardrails, and reasoning frameworks, and its performance is evaluated using synthetic digital twins that simulate realistic, labeled dialogues based on historical data. Results show a 30.6% increase in classification accuracy and high satisfaction from subject‑matter experts, demonstrating the effectiveness of targeted probing for scalable banking operations.
By Alankar Atreya, Stefan Sylvius Wagner, Devesh Batra, Robert Hankache, Cristovao Iglesias Jr, Patrick Sinclair, Giulio Pelosio, Michael McMillan, Greig A. Cowan, Raad Khraishi
The paper introduces JobMate, a persona‑grounded conversational agent that transforms peer job‑seeking posts into interactive dialogues to aid career exploration. In a study with 24 participants, JobMate helped users select relevant cases, ask follow‑up questions, and articulate constraints, contrasting with a static browsing tool that left reconstruction to users. The authors discuss design implications for blending authentic peer experiences with generative AI.
By Pengping Tan, Baoquan Zhao, Shuai Ma, Zhenhui Peng
The paper investigates how marginally correct tool-result caching can affect group-normalized policy updates in reinforcement learning. Using a two-action model, the authors show that sharing a single stochastic result per group can reverse the expected direction of policy updates, leading to a wrong-direction region and a persistent update-variance floor as group size increases. They derive exact finite-group expressions, verify them across numerous configurations, and demonstrate that centering without group standard-deviation scaling preserves the correct update direction.
By Shivam Gupta
The paper introduces two distributed recursive Gaussian process algorithms, ADMM‑RGP and PDMM‑RGP, designed for multi‑output regression in multi‑agent systems. It analyzes their stability and convergence, proposes parameter selection strategies to speed up convergence, and demonstrates that the methods reduce communication overhead while preserving estimation accuracy and consensus. Experiments on a real‑world wind dataset confirm the algorithms’ effectiveness across different communication graph connectivities.
By Josephine King, Ali Emre Balci, Raj Thilak Rajan
The paper introduces ZO-COSMO, an index‑free one‑hop mixing scheme for decentralized zeroth‑order optimization that couples two‑query estimation with average‑preserving masked consensus. It characterizes the necessary one‑hop condition for sparse communication, derives sharp contraction bounds and convergence guarantees for core and sparse‑momentum updates, and demonstrates empirical gains on synthetic agents and Qwen LoRA workers, achieving notable accuracy improvements over traditional Rand‑k and all‑neighbor mixing methods.
By Shengjun Zhang, Tingyi Liu, Heng Zhang, Dong Xie
The paper introduces CELLAUDIT, a method for auditing whether inputs claimed to influence predictive models actually do so. By testing if an input can enter the computation, whether predictions depend on it, and if that dependence improves observed responses, the authors evaluate agent-generated predictors on a morphology‑transcriptomics benchmark (BBBC047). Their findings show that many models claim compound contributions that are not supported by the data, and that falsification‑guided revisions can recover genuine input effects while improving performance.
By Mengran Li, Bo Li, Chengyang Zhang, Yang Yan, Jinfeng Xu, Zhenchao Tang
arXiv:2609.28239v1 Announce Type: new
Abstract: With the development of applications like autonomous driving, object detection has gained significant attention, while also highlighting critical vulne...
By Li Zeng, Mingcheng Duan, Longfei Fan, Hangtao Zhang, Xianlong Wang, Yanchun Li, Xia Wen, Leo Yu Zhang
arXiv:2609.27717v1 Announce Type: new
Abstract: Human-written agent skills encode rich workflows for real-world problem solving, but are typically used as external inference-time instructions rather...
By Zhilong Ge, Yuting Shao, Yutao Yang, Yuxuan Cai, Jie Zhou, Kai Chen, Bo Zhang, Qin Chen, Liang He
arXiv:2609.27667v1 Announce Type: new
Abstract: Reinforcement learning (RL) achieves strong performance in sequential decision-making but remains brittle under dynamic uncertainty and distributional...
By Jiaxi Wu, Tiantian Zhang, Yuxing Wang, Yongzhe Chang, Xueqian Wang
arXiv:2609.27051v1 Announce Type: new
Abstract: Language-model agents now run the whole of quantitative factor research: they propose investment factors, backtest them, select the survivors and retir...
By Bo Qu, Mingguang Chen, Licheng Wang
arXiv:2609.27284v1 Announce Type: new
Abstract: We present Hunyuan-A13B, an open-source large language model based on a Mixture-of-Experts architecture. It contains 80 billion total parameters but ac...
By Tencent Hunyuan Team, Ao Liu, Botong Zhou, Can Xu, Chayse Zhou, ChenChen Zhang, Chengcheng Xu, Chenhao Wang, Decheng Wu, Dengpeng Wu, Dian Jiao, Dong Du, Dong Wang, Feng Zhang, Fengzong Lian, Guanghui Xu, Guanwei Zhang, Hai Wang, Haipeng Luo, Han Hu, Huilin Xu, Jiajia Wu, Jianchen Zhu, Jianfeng Yan, Jiaqi Zhu, Jihong Zhang, Jinbao Xue, Jun Xia, Junqiang Zheng, Kai Liu, Kai Zhang, Kai Zheng, Kejiao Li, Keyao Wang, Lan Jiang, Lixin Liu, Lulu Wu, Mengyuan Huang, Peijie Yu, Peiqi Wang, Qian Wang, Qianbiao Xiang, Qibin Liu, Qingfeng Sun, Richard Guo, Ruobing Xie, Saiyong Yang, Shaohua Chen, Shihui Hu, Shuai Li, Shuaipeng Li, Shuang Chen, Suncong Zheng, Tao Yang, Tian Zhang, Tinghao Yu, Weidong Han, Weijie Liu, Weijin Zhou, Weikang Wang, Wesleye Chen, Xiao Feng, Xiaoqin Ren, Xingwu Sun, Xiong Kuang, Xuemeng Huang, Xun Cao, Yanfeng Chen, Yang Du, Zhen Yang, Yangyu Tao, Yaping Deng, Yi Shen, Yigeng Hong, Yiqi Chen
arXiv:2609.27490v1 Announce Type: new
Abstract: AI research agents need reliable knowledge of how their experiments change outcomes. We introduce WhatWorkedBench to measure experimental understanding...
By Jingjie Ning, Xueqi Li, Yibo Kong, Dongting Li
arXiv:2609.27606v1 Announce Type: new
Abstract: We introduce State-Grounded Conditioning (SGC), a design principle for user-facing LLM agents that must condition on live user state (game state, sessi...
By Qi Liu, Xiaoyang Yuan, Yubin Ruan, Zhuomeng Zhang, Wenjin Wang, Di Wu, Mingye Xu, Xinyi Mou, Xingxi Yin, Ke Feng, Zixun Sun
arXiv:2609.26900v1 Announce Type: cross
Abstract: A language model agent acts through the tools it is given. The data it reads while working on a task can redirect what it does with those tools. A gr...
By Reshabh K Sharma, Linxi Jiang, Shuo Chen, Zhiqiang Lin
arXiv:2609.27155v1 Announce Type: cross
Abstract: With recent advancements in large language models (LLMs) and LLM-based agents, these agents are becoming increasingly autonomous and gaining broader...
By Yue Xing, Pengfei He, Zitao Li
arXiv:2609.27378v1 Announce Type: cross
Abstract: End-to-end speech-to-speech dialogue models listen and speak simultaneously, so a continuously open acoustic channel is exposed to adversarial manipu...
By Kian Shamsaie, Iman Modarressi
arXiv:2609.28049v1 Announce Type: cross
Abstract: Video understanding is usually benchmarked on curated, single-actor, or professionally filmed clips, and a strong score there is routinely read as ev...
By Sai Varun Kodathala, Prashanth Pollishetty, Jaylen Cargill
arXiv:2609.27532v1 Announce Type: new
Abstract: Long-horizon agentic tasks require an agent to modify an environment through a sequence of tool calls, with success determined by the final state. The...
By Ming Ma, Yi Zhu, Yiran Zhong, Feida Zhu, Chonghan Liu, Pengkun Jiao, Qichao Wang, Yanhao Jia, Tianming Yang, Steven Hoi
arXiv:2609.27900v1 Announce Type: new
Abstract: Large language models (LLMs) are increasingly deployed in multi-agent systems where a principal agent decomposes tasks and delegates them to subordinat...
By Zonghao Ying, Jiaqi Yan, Huize Luo, Quanchen Zou, Aishan Liu, Xianglong Liu
arXiv:2609.28236v1 Announce Type: new
Abstract: Long-horizon embodied interaction requires agents to retain and continually update information about the environment as they observe, act, and encounte...
By Lizhou Liang, Xinyu Zhong, Miao Pan, Xiaohe Zhou, Xuanyu Liu, Qinfeng Li, Peng Li, Jintao Chen, Xuhong Zhang, Wenqi Zhang