The paper introduces GACA, a critic‑free reinforcement learning estimator that adapts credit assignment granularity based on a step‑level uncertainty proxy. GACA assigns higher weight to fine‑grained signals for steps with above‑average negative log‑likelihood, while relying on episode‑level signals for less uncertain steps, improving task success on ALFWorld and WebShop for 1.5B and 7B language models. The authors provide a risk decomposition, a conditional bound on action‑value variation, and an error‑projection analysis to justify the method’s effectiveness.
By Taoran Liang, Yang Liu, Shang Luo, Yingguang Yang, Rongrong Zhang, Yingzong Min, Yulin Huang, Jianshen Zhang, Yongzhi Qi, Kefu Xu, Congjing Ran, Bin Chong
The study evaluates a multi‑agent large language model system for forecasting outcomes of the 2026 FIFA World Cup. Two specialist agents—one quantitative and one news‑focused—produce forecasts that are then reviewed by a critic and combined by a meta‑agent. Results show the news specialist performs best, matching betting market accuracy, while the meta‑agent adds little beyond the specialists’ predictions.
By Julian Varghese, Lucas Bickmann, Sarah Sandmann
EventMemAgent is an active online video agent that uses a hierarchical memory module to handle continuous perception and long‑range reasoning in streaming video. The framework employs a short‑term memory layer to detect event boundaries and sample frames within a fixed buffer, while a long‑term memory layer archives observations event‑by‑event. It also incorporates a multi‑granular perception toolkit and Agentic Reinforcement Learning to internalize reasoning and tool‑use strategies, achieving competitive results on online video benchmarks.
By Siwei Wen, Zhangcheng Wang, Xingjian Zhang, Lei Huang, Wenjun Wu
PEARL is a framework for human‑centric cyber‑physical systems that uses a dual‑path Early‑Exit Deep Q‑Network to control the trade‑off between privacy and utility. By training per‑branch binary labels—Utility Confidence Labels (UCL) and Privacy Confidence Labels (PCL)—based on mutual information between private states and observable actions, PEARL selects the shallowest exit that satisfies both privacy and utility constraints, avoiding noise injection. The system includes an MI‑based feedback loop to detect behavioral drift and trigger retraining, and experiments on a smart‑home HVAC system and a VR smart classroom show a 25.67% reduction in adversarial state‑inference accuracy with only a 10‑16% utility cost.
By Mojtaba Taherisadr, Salma Elmalaki
The paper introduces Batched SGD, a variant that groups online samples into epochs and performs a single update per epoch using a low‑variance gradient estimate. This batching approach allows a straightforward high‑probability analysis without restrictive assumptions or auxiliary sequences, yielding near‑optimal rates for both strongly convex and non‑convex objectives under standard smoothness and sub‑Gaussian noise conditions. The authors also extend the method to federated learning, providing the first high‑probability guarantees with logarithmic communication complexity, linear speedup in the number of agents, and robustness to data heterogeneity.
By Feng Zhu, Robert W. Heath Jr., Aritra Mitra
arXiv:2609.12475v1 Announce Type: new
Abstract: Comprehensive benchmark suites are essential for improving large language models (LLMs), but many widely used benchmarks are redundant, making evaluati...
By Zhongzhan Huang, Junxin Li, Guoming Ling, Yupei Lin, Shanshan Zhong, Hefeng Wu
arXiv:2609.13117v1 Announce Type: new
Abstract: Full-duplex evaluation often emphasizes whether an agent keeps speaking or stops. That binary cannot express a third response humans use routinely: con...
By Yunqi Lu, Tyler Baumgartner, Nikhil Johri, Brandon Tai, Candice Fan, Luc Debaupte, Ruben Aguilar, Bill Wang, Yi Zhong
arXiv:2609.11987v1 Announce Type: cross
Abstract: An agentic coding system couples a language model to a harness: the tools, prompts and control flow that turn a chat model into an autonomous softwar...
By Mohsen Arjmandi
arXiv:2609.12444v1 Announce Type: cross
Abstract: Simulated societies of large language model agents are used to study online polarization, and separately to study collective intelligence, but the tw...
By Raad Bin Tareaf
arXiv:2609.13076v1 Announce Type: cross
Abstract: Conversational voice agents have advanced significantly, offering increasingly natural human-machine interactions through both cascaded and end-to-en...
By Yi-Jen Shih, Shih-Yun Shan Kuan, Guan-Ting Lin, Kai-Wei Chang, Siddhant Arora, Shu-wen Yang, Abdelrahman Mohamed, Shinji Watanabe, Hung-yi Lee, David Harwath
arXiv:2606.23189v2 Announce Type: replace-cross
Abstract: Computer-use agents (CUAs) now act on a user's behalf across personal applications such as email, calendars, and to-do lists. This cross-appl...
By Anmol Goel, Iryna Gurevych
arXiv:2609.12818v1 Announce Type: new
Abstract: Long video understanding often behaves like a visual needle-in-a-haystack problem: query-relevant evidence is sparsely distributed across long temporal...
By Sen Yang, Boqiang Duan, Jing Yang, Weihao Bo, Jie Liu, Boyuan Tong, Ze Feng, Wenkang Zhang, Jingdong Wang, Hua Wu
arXiv:2609.13013v1 Announce Type: new
Abstract: Flat roofs are among the most influential components of the building envelope, governing both structural performance and thermal efficiency, and thereb...
By Samuel Dunthorne, Hashim A. Hashim
The paper introduces PACEvolve, a framework that improves self‑evolving agents powered by Large Language Models by addressing their tendency to become trapped in local contexts and repeat flawed hypotheses. It does so through three techniques: Hierarchical Context Management to prune memory, Momentum‑Based Backtracking to escape local minima, and a self‑adaptive Collaborative Evolution policy to balance refinement and knowledge transfer. These methods enable the agents to maintain a global view of search momentum and achieve state‑of‑the‑art results on complex evolutionary benchmarks.
By Minghao Yan, Bo Peng, Benjamin Coleman, Ziqi Chen, Zhouhang Xie, Shuo Chen, Zhankui He, Noveen Sachdeva, Isabella Ye, Weili Wang, Chi Wang, Ed H. Chi, Fernando Pereira, Wang-Cheng Kang, Derek Zhiyuan Cheng, Beidou Wang
The paper introduces a belief‑shift evaluation benchmark for large language models (LLMs) using the social‑deduction game Werewolf. By annotating suspicion and accusation messages in LLM‑played games, the authors measure how a village‑side model’s beliefs change after each message, evaluating 40 open‑weight LLMs on 1,224 annotated messages. Results show that larger models better distinguish wolves from villagers, yet accusations still heavily sway beliefs, especially when the accuser is trusted, and even when the accuser is wolf‑aligned.
"whyItMatters":"The study highlights that current open‑weight LLMs up to 120B parameters still struggle to integrate accusation content with source trust in strategic communication, revealing limitations in their belief‑updating capabilities in complex social contexts."
By Yu-Yu Yang, Ti-Rong Wu, Hung Guei, Hsing-Yu Chen, I-Chen Wu
Semantically Aligned Gradient-Driven Context-Preserving Image Editing (IABEdit) is a model‑agnostic framework that embeds differentiable semantic verification into the training of generative image editors. By using a frozen vision‑language model to extract spatially‑aware descriptors from ground‑truth edits and a trainable aligner to reproduce them from generated outputs, the residual becomes a gradient that teaches the generator both what to edit and where, without adding inference‑time VLM cost. IABEdit is compatible with various backbones (e.g., U‑Net in Stable Diffusion and MMDiT in FLUX) and improves structural fidelity on MagicBrush, achieves state‑of‑the‑art instruction adherence on RealEdit and EMU Edit, and outperforms the proprietary Gemini agent on the D‑LORD surveillance benchmark under heavy occlusion.
"whyItMatters":"IABEdit demonstrates that incorporating semantic verification during training can produce more accurate, well‑localized edits and outperform existing methods even in challenging surveillance scenarios, as shown by its superior metrics and human/GPT‑4o evaluations."
By Chiranjeev Chiranjeev, Muskan Dosi, Mayank Vatsa, Richa Singh
RoMu4o is a ground robot equipped with a 6‑DOF arm and a vision system that performs real‑time deep‑learning image processing and motion planning for proximal hyperspectral leaf sensing in orchards. The system uses robust perception and manipulation pipelines to identify leaf 3D structure, propose 6‑D poses, and generate collision‑free, constraint‑aware paths for precise leaf grasping and spectroscopy. In lab trials the robot achieved a 95 % success rate for 1‑LPB hyperspectral sampling, while field trials in a pistachio orchard reached 70 % success for autonomous leaf grasping and measurement.
whyItMatters":"The system demonstrates a viable robotic solution to automate leaf‑level hyperspectral sensing, addressing labor shortages and enabling precise crop health monitoring in precision agriculture."
By Mehrad Mortazavi, David J. Cappelleri, Reza Ehsani
BodhiPromptShield is a policy‑aware mediation layer for LLM agent pipelines that detects sensitive text spans before they propagate, replacing them with typed placeholders, semantic abstractions, or secure tokens and restoring them only at authorized execution boundaries. In evaluations on AI4Privacy, PrivacyLens, and AgentDojo datasets, the system reduces identifier exposure to 7.4% and 1.8% respectively, and limits exact identifier leakage in final actions to 2.1–3.1%. While mediation preserves factual content according to automated metrics, human annotations show a significant drop in inferability from 100% to 24–53%, indicating the need for human validation of semantic‑leakage measures.
By Bo Ma, Jinsong Wu, Weiqi Yan
The paper investigates how fully autonomous machine‑learning research systems can tackle open‑ended, industry‑grade problems, using telecom ticket retrieval as a case study. It finds that while autonomous research excels at hyperparameter tuning, it lacks human intuition and creativity, yet can achieve about 90% of state‑of‑the‑art performance in a fraction of the time and at modest cost. The authors recommend a hybrid approach where human researchers collaborate with autonomous frameworks for optimal results.
By Junghyun Min, Huseyin Uzunalioglu, Mohamed Trabelsi
The paper investigates whether an agent can learn a numerical search strategy through executable practice and then encode that strategy as text. By repeatedly writing and evaluating optimizer programs, the agent distills a 197‑word text called Harness A, which significantly reduces regret for Gemini Flash and other language‑model executors, matching the performance of classical Gaussian‑process Bayesian optimization. An independent replication produced a different but equally effective text, Harness B, and the framework also achieved the lowest regret on a sealed YouTube reward‑tuning benchmark.
By Yi Wu, Zheng Ren, Zhiyu Hu, Haochen Wang, Daryl Chang, Li Wei, Ting Wang, Zhen Li, Pooja Gupta, Nitin Jindal, Lukasz Heldt