The paper introduces HER-PDE, a scientific-agent framework that simultaneously discovers partial differential equation (PDE) structures and their unknown spatial coefficient fields. Using two noisy trajectories from different excitations, the agent generates expression-tree hypotheses, evaluates them via a Hypothesis Evaluation Interface that only estimates declared fields, and refines candidates through bidirectional cross-excitation transfer. In controlled experiments on five two-dimensional systems with Gaussian noise, HER-PDE accurately recovers the governing operators and attains a median Pearson correlation of ~0.85 and a median relative L2 error of ~0.28 for nine unknown coefficient fields.
By YuJie Huang, WenWu He, ZhuoEr Lin, Congcong Liu, Dong Liang, Zhuo-Xu Cui
The paper introduces OccLinker, a lightweight plugin for vision‑based occupancy networks that reduces flickering by efficiently merging historical static and motion cues with current features via a dual cross‑attention mechanism. It generates correction components to refine base network predictions and proposes a new temporal consistency metric to quantify flickering. Experiments on two benchmark datasets show that OccLinker improves performance with minimal computational overhead while effectively diminishing flickering artifacts.
By Fengcheng Yu, Haoran Xu, Canming Xia, Ziyang Zong, Guang Tan
The paper introduces SILICA, an open instrument designed to evaluate whether large language model (LLM) agent societies replicate human behavioural distributions. Using five environments with human‑anchored data and perturbations, the study finds that most LLMs only match human behaviour at initial stages, failing to reproduce end‑state cooperation or correct acceptance thresholds. The results suggest that current LLM societies can support exploratory claims but do not yet reliably emulate human social dynamics.
By Raad Bin Tareaf
LongDS-Bench is a new benchmark for evaluating long-horizon, multi-turn data analysis by agents, featuring 68 tasks derived from real-world Kaggle notebooks that span 2,225 turns across six domains such as Geoscience, Business, and Education. The benchmark focuses on agents’ ability to maintain, update, restore, and compose evolving analytical states, with tasks designed around state-evolution patterns like counterfactual perturbation, rollback, and multi-state composition, and an average dependency span of 11.3 turns. Evaluation of five state-of-the-art models shows that the best model achieves only 48.45% average accuracy, with performance dropping nearly 47 points from early to late turns and long-horizon errors accounting for 52%–69% of failures, indicating that maintaining a correct analytical state is the key bottleneck.
By Kewei Xu, Xiaoben Lu, Shuofei Qiao, Zihan Ding, Haoming Xu, Lei Liang, Ningyu Zhang
The paper investigates how agent memory contributes to reliable handling of unanswerable questions (UAQs) within a unified Retrieval-Augmented Generation (RAG) framework. Four memory methods were evaluated across three UAQ datasets and two base models, revealing that memory can improve UAQ performance in selective settings but the gains are fragile under dataset shift. Procedural and rule-based memories, especially when combined with complementary behavioral signals, provide the most reliable support, indicating that effective UAQ memory relies more on transferable behavioral guidance than on sheer volume of stored experience.
By Chuanyuan Tan, Junjie Yu, Yuxin Wang, Yining Zheng, Xipeng Qiu, Wenliang Chen
The paper investigates whether large language models (LLMs) replicate socio‑cognitive effects of power asymmetry observed in human communication. By assigning high or low status personas to LLMs in simulated multi‑turn dialogues across diverse professions, the study measures language coordination, pronoun usage, persuasion success, and compliance with unsafe requests. Results indicate that LLMs exhibit key power‑related socio‑cognitive behaviors, though with nuances and variability, linking these simulated interactions to both desirable and unsafe outcomes.
By Anvesh Rao Vijjini, Sagar Manjunath, Snigdha Chaturvedi
The paper introduces Cognitive Chain-of-Thought (CoCoT), a structured reasoning framework for vision‑language models that divides multimodal social reasoning into three cognitively inspired stages: Perception, Situation, and Norm. CoCoT improves performance across diverse tasks—multimodal intent disambiguation, theory of mind, social commonsense reasoning, and safety instruction following—by 5.9% to 4.6% on average. Fine‑tuning on CoCoT‑structured traces further boosts accuracy by 5–6% without explicit prompting, indicating that models internalize the structured reasoning pattern and that the approach enhances interpretability and social alignment in multimodal systems.
By Eunkyu Park, Wesley Hanwen Deng, Gunhee Kim, Motahhare Eslami, Maarten Sap
The paper introduces the KITScenes LongTail dataset, a curated collection of rare driving scenarios designed to evaluate how well reasoning models in autonomous driving follow their own reasoning. The authors find that many current models frequently diverge between the actions they state in their reasoning chains and the actions they actually execute, a phenomenon they term incoherence. They show that when the reasoning and execution disagree, the reasoning is often correct, and enforcing coherence via a kinematic model can improve motion planning, indicating that coherent action based on stated reasoning is essential for trustworthy autonomous driving.
By Royden Wagner, Omer Sahin Tas, Jaime Villa, Felix Hauser, Yinzhe Shen, Marlon Steiner, Dominik Strutz, Carlos Fernandez, Quentin Delfosse, Christoph Weinhuber, Christian Kinzig, Guillermo S. Gutierrez-Cabello, Hendrik K\"onigshof, Fabian Immel, Richard Schwarzkopf, Nils Alexander Rack, Kevin R\"osch, Kaiwen Wang, Jan-Hendrik Pauls, Martin Lauer, Igor Gilitschenski, Holger Caesar, Christoph Stiller
The paper presents a post‑training recipe for small dialogue‑game agents that involves three steps: acquiring broad game participation via supervised fine‑tuning, repairing specific local failures with turn‑local preference pairs, and preserving general capabilities. Applied to the LM Playschool Challenge, the method raises the public clemscore from 10.67 to 38.92 and the closed in‑domain score from 13.41 to 41.17 while keeping overall static performance nearly unchanged. The gains are mainly within the targeted game family, with limited improvement on out‑of‑domain clemscore.
By Nan Li
arXiv:2608.27997v1 Announce Type: new
Abstract: Air-ground cross-view referring person detection is a necessary component in the language-to-perception-to-control chain of collective embodied intelli...
By Zhoupeng Guo, Xinjie Yao, Yunqi Zhu, Zhihe Fan, Siqi Zhao, Jianjun Chen, Yichen Dong, Yan Fan, Pengfei Zhu
arXiv:2608.28198v1 Announce Type: new
Abstract: Privacy-preserving learning is often motivated by the idea that protecting users' data can preserve trust and thus participation, improving utility in...
By Uddalak Mukherjee, Edwige Cyffers, Yann Chevaleyre
D3‑Gym is the first automatically constructed dataset that provides verifiable environments for scientific data‑driven discovery, comprising 565 tasks from 239 real scientific repositories across four disciplines. Each task includes a natural‑language instruction, an executable environment with pre‑installed dependencies, dataset previews, a reference solution, and an automatically synthesized evaluation script that achieves 87.5% agreement with human‑annotated gold standards. Training on trajectories sampled from D3‑Gym consistently improves Qwen3 models on ScienceAgentBench, and the platform also serves as a testbed for studying agentic optimization loops such as Autoresearch on real scientific workflows.
By Hanane Nour Moussa, Yifei Li, Zhuoyang Li, Yankai Yang, Cheng Tang, Tianshu Zhang, Nesreen K. Ahmed, Ali Payani, Ziru Chen, Huan Sun
arXiv:2606.17092v2 Announce Type: replace-cross
Abstract: Agentic systems are increasingly integrated with geographic information systems (GIS), where multi-agent coordination enables complex convers...
By Kyle Gao, Pranavi Kotta, Linlin Xu, Jonathan Li, David A. Clausi
arXiv:2608.27871v1 Announce Type: new
Abstract: Long-video understanding remains challenging for Multimodal Large Language Models (MLLMs) due to limited context length. Uniform sampling may miss cruc...
By Ziling Huang, Shin'ichi Satoh
arXiv:2608.27584v1 Announce Type: new
Abstract: Autonomous systems rely on extracting information from light, yet remain brittle in extreme environments, from nighttime navigation to high-speed robot...
By Varun Sundar, Pavan Thodima, Sacha Jungerman, Mohit Gupta
arXiv:2608.27549v1 Announce Type: new
Abstract: Physical understanding and reasoning depend on forming compact and generalizable representations of the world. While modern vision-language models can...
By Hanyang Wang, Yimo Cai, Weiliang Chen, Jiawei Chi, Haowen Sun, Qiyu Dai, Yi-Hsin Hung, Xingzhuo Guo, Jinshan Ren, Runmao Yao, Ziwei Liu, Mingsheng Long, Yueqi Duan, Jun Gao, Jiangran Lyu, Fangfu Liu, Jialong Wu
LandingAgent is a new framework for generating landing pages that are tailored to a specific target. It uses a reference‑annotated dataset called LandingBench, which abstracts real landing pages into structured elements such as section sequences, layout patterns, tone descriptors, visual emphasis, and CTA structure. The agentic framework operates in three phases—profiling the target, building a reference‑guided wireframe, and refining the page through critique—resulting in pages that are more faithful to the target, concise, readable, aesthetically pleasing, and structurally diverse compared to direct prompting.
By Injun Baek, HyeongSeok Lee, Yearim Kim, Junhoo Lee, Nojun Kwak
uScenes is a new multimodal dataset for underwater robot perception that provides synchronized 3D multibeam sonar point clouds and RGB imagery. It comprises 110 scenes with 95,834 observations, totaling 277.6 minutes of data collected during multiple field sessions. The dataset aims to support research in underwater sensor fusion, cross‑modal representation learning, and 3D scene understanding.
By Trung Tien Dong, Zhenqi Wu, Aditya Penumarti, Zi-Hao Zhang, Micaiah Bartlett, Jane Shin, Xiaomin Lin
The paper introduces PASK (Parser-Aware Structural KV Persistence), a method that leverages parser transitions to inform key‑value (KV) persistence decisions in structured generation tasks. By aligning KV compression with task‑level structured risk, PASK sets protection floors based on error sensitivity and allocates remaining KV capacity using attention‑output distortion, producing a lightweight, structure‑conditioned lookup policy. In experiments on Qwen3‑4B, PASK achieves a 17.39‑point accuracy gain over the best compressed baseline, while delivering up to 2.2× higher throughput, 3.3× lower TPOT, and 0.53× the peak GPU memory of full KV.
By Linze Wu, Xinrui Chen
The paper introduces Qwen-GuidePlay-2B, a 2B‑parameter language model fine‑tuned for dialogue‑game interaction. The training pipeline consists of three stages: supervised fine‑tuning on successful game trajectories, weighted turn‑level fine‑tuning, and teacher‑guided fine‑tuning that corrects formatting and evaluates examples. The resulting model achieves a clemscore of 57.12 and a statscore of 42.68 on Playpen’s public validation, ranking second in the official challenge and demonstrating that careful curation can outperform more aggressive procedural methods.
By Syed Mahbubul Huq, Pranava Madhyastha