DGSG-Mind introduces a hybrid instance-aware 3D Gaussian dynamic scene graph system that integrates open‑vocabulary semantic information into dynamic 3D scene representations. By coupling a probabilistic voxel grid with explicit 3D Gaussians, it achieves robust cross‑modal instance fusion, incremental semantic mapping, and dynamic change handling through Gaussian‑based relocalization and masked refinement. The system builds a hierarchical scene graph and a 3D Gaussian Mind for multimodal reasoning, achieving state‑of‑the‑art zero‑shot 3D visual grounding and strong performance in open‑vocabulary semantic segmentation and scene reconstruction, and is demonstrated on real‑world robots.
By Luzhou Ge, Xiangyu Zhu, Jinyan Liu, Xuesong Li
The paper introduces Decision‑Relevant Fresh Comparison (DRFC), a method for decentralized bandit systems with heterogeneous agents whose local reward changes may not affect the global best action. DRFC gathers balanced samples from all agents and only switches the common best arm when fresh global evidence indicates a change, yielding a dynamic regret bound that does not depend on the number of local changes. An anytime‑valid sliding‑window extension further handles gradual drift, and experiments on synthetic, semi‑real, and MovieLens‑1M data demonstrate that DRFC ignores decision‑irrelevant local changes while the extension avoids false switches.
By Zhaojun Peng
OmniHarness is a framework that enables generalizable visual generation by learning symbolic policies from verified executions. It abstracts shared procedures and applicability conditions, allowing these policies to be instantiated, adapted, and composed for new tasks while keeping model parameters fixed. The system uses intermediate verification for refinement, self-directed inquiry to generate practice tasks, and continuous feedback to expand capabilities, achieving strong results on multiple benchmarks and outperforming baselines on Creative tasks.
By Xu Xu (Beihang University), Jinxiu Liu (The Chinese University of Hong Kong), Zhangbo Qiao (Beihang University), Jiaxing Lu (Beihang University), Xiangyu Zhang (Beihang University), Yubin Gu (National University of Singapore), Fangwei Ning (Beihang University), Yan Shi (Beihang University)
The paper introduces ASURRE, a benchmark dataset for detecting AI‑assisted responses in online surveys. It evaluates how different LLM usage strategies—ranging from full generation to persona‑grounded agentic completion—affect the performance of existing machine‑generated text detectors. The study finds that while naive AI usage is easily detected, more sophisticated persona‑grounded agents approach chance performance, yet still leave identifiable behavioural traces that can be aggregated to improve detection.
By Qizhou Wang, Bogdan Mamaev, Christopher Leckie
The study investigates how pruning affects large language models (LLMs) used for smart‑home tool calling. Researchers examined four LLMs—dense Transformer, dense hybrid, and mixture‑of‑experts (MoE) architectures—using depth, width, hybrid, and expert pruning, followed by supervised fine‑tuning. They evaluated over 19,500 instances from three smart‑home datasets, analyzing not only overall accuracy but also degradation in action components (operation, device, argument, value) and task complexity, finding that dense models suffer sharp performance drops after a narrow safe pruning range, while MoE models tolerate more pruning; aggressive pruning also leads to over‑refusal and loss of grounded specificity.
By Congjing Zhang, Vashishtha Patil, Henning Lange, Usman Aleem
The paper introduces ATRBench, a benchmark that measures the proactivity gap in long‑lived LLM agents by evaluating their ability to ask for user preferences that are not needed immediately but may be useful in future sessions. It defines the Ask‑to‑Remember (ATR) task, where agents must decide whether to request a reusable preference now, and shows that current state‑of‑the‑art agents perform significantly below an oracle. The study identifies preference acquisition as the main bottleneck and provides a diagnostic framework for improving agent proactivity.
By Bin Wu, Guanyun Zou, Bingbing Wang, Huan Zhao, Chuan Shi
The paper presents a symmetric solution to the Bellman optimality equation for a repeated harmony game, revealing three distinct symmetric solutions. One solution corresponds to the trivial All‑Cooperate strategy, another aligns with the Win‑stay Lose‑shift strategy known from the prisoner's dilemma, and a third nontrivial strategy is explored in detail. The authors also numerically examine which of these strategies agents learn using a reinforcement learning algorithm.
By Hisato Komatsu
arXiv:2408.14575v5 Announce Type: replace
Abstract: EVINCE (Entropy and Variation IN Conditional Exchanges) is a novel framework for optimizing multi-LLM dialogues using conditional statistics and in...
By Edward Y. Chang
arXiv:2609.16302v1 Announce Type: cross
Abstract: When a coding agent returns to existing software, it inherits evidence from earlier engineering work: tests, type checks, proofs, static analyses, an...
By Anjan Goswami
arXiv:2609.16313v1 Announce Type: cross
Abstract: In agentic distributed systems, an agent may be authorized to mutate external infrastructure while lacking evidence that the mutation is ready to exe...
By Jun He, Deying Yu
arXiv:2609.16625v1 Announce Type: cross
Abstract: How and why does a recommender system fail the users it serves? Oftentimes, practitioners are left to improve their algorithms based on a combination...
By SungGeun Kim, Abhinav Narain, Daniel Nemirovsky
arXiv:2609.16369v1 Announce Type: new
Abstract: Precise manipulation of liquid droplets underpins lab-on-a-chip platforms for diagnostics, chemical synthesis, and biological assays. Yet autonomous dr...
By Rajneesh Anand, Mayuresh V. Kothare
arXiv:2609.17088v1 Announce Type: new
Abstract: Recent advancements in large language models have significantly enhanced the capabilities of agents in modeling long-term conversations. Despite these...
By Cai Ke, Jiangyue Yan, Han Zhang, Xin Liu, Zike Yuan, Yue Yu, Hui Wang, Ruifeng Xu
arXiv:2609.17391v1 Announce Type: new
Abstract: Model serving is one of the largest cost drivers in production recommender systems. Maximizing its throughput requires navigating a deeply layered hier...
By Qi Wu, Lohan Lemire, Kai Meng, Zhongmou Cai, Raphael Bargues, Petr Zhitnikov, Zeyuan Cao, Yao Wang, Shujun Bian, Wei Chen, Sean Sheng
arXiv:2609.17496v1 Announce Type: new
Abstract: LLM assistants are widely used for daily social advice, yet evaluating their social reasoning in such consultation settings remains challenging since (...
By Amir Taubenfeld, Zorik Gekhman, Avigail Grinstein-Dabush, Itay Laish, Ariel Goldstein, Marian Croak, Avinatan Hassidim, Yossi Matias, Amir Feder
arXiv:2609.16936v1 Announce Type: cross
Abstract: Large language model (LLM)-powered coding agents have made rapid progress in automating software engineering tasks, yet repository-level issue resolu...
By Yunxiang Zhang, Haiquan Wang, JiaWei Guo, Hanyang Xia, Yan Chen, Tong Chen, Zhang Zhiwei, Junchen Ye
arXiv:2609.16215v1 Announce Type: new
Abstract: GPU high bandwidth memory is scarce and expensive, and KV caches consume much of it as chats, agent loops, and document question answering accumulate s...
By Srikanta Datta Tumkur, Jay Iyer, Mehar Simhadri, Sai Pavan Kumar, Sai Kapil Kumar, Ramesh Nampelly
arXiv:2609.16487v1 Announce Type: new
Abstract: We present a framework for evaluating data-science agents on live, continuously updated data using executable ground truth and format-agnostic factoid...
By Aniruddha Tamhane, Raghavendra Addanki, Ayushi Aggarwal, Aditya Bansal, Rui Wang, Charles Menguy, Swati Jain
arXiv:2609.16563v1 Announce Type: cross
Abstract: We have developed the MAL Simulator, a cyber operation simulator based on the Meta Attack Language (MAL). The MAL Simulator is intended for decision-...
By Jakob Nyberg, Sandor Berglund, Andrei Buhaiu, Joakim Loxdal, Pontus Johnson, Mathias Ekstedt
arXiv:2609.16697v1 Announce Type: cross
Abstract: World models connect perception and decision-making in embodied intelligence by maintaining hidden state, anticipating consequences, comparing interv...
By Nanjie Yao, Hao Wang, Chong Cheng, Zhikang Chen, Wenzhe Li, Jiafei Lyu, Li Shen, Peilin Zhao, Zongqing Lu, Gao Huang, Steven Hoi, Dacheng Tao, Deheng Ye