Tree-of-Concerns is a multi‑agent framework that uses specialized skeptic personas to conduct parallel debate trees, each focusing on a specific category of potential limitations in scientific papers. The system employs structured, evidence‑grounded argumentation and a panel review mechanism to correct drift and miscalibration, ultimately extracting unstated limitations. Experiments on the ToC‑Bench benchmark show that the approach improves precision by 79% and coverage by 11% over leading baselines, providing reviewers with specific, evidence‑based concerns for systematic evaluation.
By Sahil Mishra, Niranjan Rajeev, Tanmoy Chakraborty
The paper introduces Driving with DINO (DwD), a framework that uses Vision Foundation Module (VFM) features to bridge simulation and real-world domains for autonomous driving video generation. It addresses the consistency‑realism dilemma by projecting VFM features onto a principal subspace, dropping high‑frequency texture elements, and applying a Random Channel Tail Drop to preserve structural detail. Additional components— a learnable Spatial Alignment Module and a Causal Temporal Aggregator— enhance control precision, spatial alignment, and temporal stability, reducing motion blur and ensuring realistic, consistent outputs.
By Xuyang Chen, Conglang Zhang, Chuanheng Fu, Zihao Yang, Kaixuan Zhou, Yizhi Zhang, Yanfeng Zhang, Mingwei Sun, Zhen Dong, Xiaoxiao Long, Zengmao Wang, Liqiu Meng
arXiv:2605.13872v2 Announce Type: replace-cross
Abstract: This article introduces S-AI-Recursive, a bio-inspired Sparse Artificial Intelligence architecture in which reasoning is implemented as a hor...
By Said Slaoui
The paper introduces a new failure mode in agentic memory systems called structurally indirect prerequisite eviction, where upstream memory blocks that are only weakly aligned with a query are prematurely discarded due to budget constraints. The authors define this failure operationally, present a deterministic benchmark and trace diagnostics, and evaluate a one‑hop graph‑aware rule called Dependency‑aware Semantic Garbage Collection (DSGC). DSGC dramatically improves full‑chain retention rates across different encoders, and the study identifies the budget and scaling regimes where the rule is effective or fails.
By Minkyu Song
The paper introduces a multi‑modal traffic sign detection framework that fuses camera and LiDAR data using an Intensity‑Aware Deformable Fusion module to align retro‑reflective LiDAR cues with visual features. It also presents a dual motion‑model tracker to handle non‑linear perspective changes and a semantic attribute classification pipeline that estimates occlusion, readability, sign embeddedness, and road relevance. Evaluated on a dataset covering more than 60 countries and 2,500 hours of driving, the system achieves an Object Miss Ratio of 0.49% across 221,068 sequences, indicating strong global generalization for autonomous driving.
By Meda Lazar, Sourab Sridhar, Shashwata Gupta, Alexandra Tripcea, Varun Ravi, Senthil Yogamani
The paper introduces OneModel, a paradigm that consolidates complex business workflows and SOPs into a single model’s parameters, replacing traditional modular pipelines. By using Continual Pre‑Training and logic‑compilation SFT, the authors transform fragmented rules into unified attention‑based reasoning. In a global financial service deployment, OneModel cuts end‑to‑end latency by over 50 % and raises the Intelligent Resolution Rate from 64.3 % to 83.3 %.
By Chang Liu, Chaoyang Ning, Dayi Jiang, Enrui Gu, Fang Ran, Hongyan Xue, Huaqing Li, Hui Cai, Jia Liu, Jiang-Ming Yang, Jianshe Li, Jiawei Luo, Jin Zhou, Leshen Zhu, Lihui Chen, Liying Ma, Lyuxin Xue, Mengjian Ji, Ruijia Xu, Wei Ren, Wei Wu, Xiaoling Qu, Xiaoyun Feng, Xin Zhang, Xixie Zhou, Xuanwei Hu, Yan Chen, Yichao Wang, Yongqi Tong, Yu Liu, Yuhong Zhou, Zemin Sun, Zhenwen Xu, Zhiling Liu, Zifan Wang
The paper introduces the Weighted Memory Tree (WMT), a hierarchical memory system for large language model agents that organizes execution histories into tasks, subtasks, and actions while assigning each memory a dynamic retention score. Event-based updates and selection-based decay allow WMT to preserve useful information, fold completed trajectories, suppress low-utility content, and retain access to folded context. Experiments on GAIA-Text with Qwen3-8B, Gemma 4 E4B, and Llama-3.1-8B show that WMT improves accuracy by an average of 9.97 percentage points and reduces prompt-token usage by 32.8%, while also limiting the persistence of unreliable information.
By Quang Dao, Purvi Kathalkar, Kenneth Eaton
BC-Bench is a new benchmark for assessing agentic engineering systems on the domain‑specific language AL used in Microsoft Dynamics 365 Business Central. It contains 101 manually curated tasks drawn from real Microsoft production repositories and evaluates not only code generation but also test creation and multimodal problem statements. The study shows that performance gaps between models are larger than those between different agent harnesses, and that gains on general‑purpose benchmarks do not reliably transfer to the AL domain.
By Haoran Sun, Klaus Marius Hansen
The paper discusses how large enterprises can adopt the harness paradigm to overcome limitations of traditional coding approaches. It reviews recent findings that harnesses outperform complex architectures at the task level, that harness choice drives benchmark variance more than model choice, and that governance is the main barrier to enterprise adoption. The authors propose a unified harness architecture that keeps code identical across deployments, simplifying review and audit processes.
By George Juraj Salapa
The paper introduces a framework for evaluating AI systems that not only checks final labels but also tracks the reasoning behind them through three core sources—grounds, norms, and authority—forming an eight-cell counterfactual judgment cube. It defines minimal source replacement sets, called judgment receipts, to explain changes in verdicts and provides certification cost bounds for black-box evaluators. The authors present ReasonBench, a benchmark with 19,520 cases, and demonstrate that while high standard accuracy can mask robustness issues, receipt accuracy reveals significant gaps in reasoning consistency across different models.
By Ye Chen, Weining Zhang
The paper investigates how small lexical changes in prompts can cause large performance swings in large language models. Using a dataset of 132,000 prompt variants, the authors uncover a scaling law linking higher average task performance to lower variance and greater robustness. They identify domain-specific terminology and explicit action directives as key linguistic factors that stabilize prompts, and propose an automated Prompt-Refining Agent that reduces performance variance by 40.7% in code generation while maintaining or improving mean performance.
By Qipeng Xie, Zi Liang, Jiafei Wu, Yufei Chen, Weizheng Wang, Wenao Ma, Zhong Ming, Haiqin Yang, Kaishun Wu
ARGUS is a new agent-based framework for persuasive argument generation that incorporates a Theory-of-Mind Reasoner to model audience beliefs and values. It uses a component-aware planner to break arguments into subtopics, assign rhetorical functions (logos, pathos, ethos, kairos), and guide evidence retrieval during planning. A refinement module iteratively addresses multi-dimensional weaknesses, and evaluations on three benchmarks show ARGUS outperforming strong baselines and effectively shifting resistant audience stances.
By Zhe Hu
The paper introduces a method to improve test-time scaling (TTS) for large language models by using multi-agent systems (MAS) to split long reasoning chains into manageable contexts. A new dataset, M500, containing 500 multi-agent collaborative reasoning traces, is used to fine‑tune open‑source models, enabling them to learn collaborative patterns and outperform their base versions. An adaptive scaling strategy with a "CEO" agent is proposed to dynamically guide reasoning depth, and experiments in the AgentVerse framework confirm the effectiveness of the approach.
By Can Jin, Hongwu Peng, Qixin Zhang, Yujin Tang, Dimitris N. Metaxas, Tong Che
Tree-of-Experience (ToE) is a hierarchical experience-management framework designed for large language model agents that aligns stored experiences with the agents’ reasoning hierarchy. By organizing experiences into a shared tree of analytical perspectives and reasoning paths, ToE calibrates reliability through environmental outcomes, enabling systematic updating, cross-task transfer, and efficient retrieval. Experiments on Game of 24 and FinEvolveBench demonstrate that ToE yields significant performance gains—31.4% accuracy improvement on Game of 24 and a 41.24% average improvement in tsIC on FinEvolveBench—outperforming both experience-free baselines and conventional experience-management methods.
By Zihao Deng, Yining Zhu, Leiming Wang, Junbo Wang, Jingfei Lu
The paper introduces MOSAIC, a benchmark that tests how vision‑language models translate theory‑of‑mind (ToM) reasoning into coordinated social actions across verbal and nonverbal channels. Across 200 trials per model, 13 models—including 11 VLMs—failed to align their behaviors with ToM constraints, revealing bottlenecks in generating coherent nonverbal signals and interpreting others’ actions. A structured model with an explicit ToM module, PCM‑LLM, succeeded in all conditions, indicating that belief‑action coupling is crucial for these tasks.
By Tonglin Yan, Gregoire Sergeant-Perthuis, David Rudrauf
arXiv:2608.20483v1 Announce Type: cross
Abstract: We develop analytical and particle-based methods for uncertainty propagation in random neural network models, where both the inputs and network param...
By Janice Adams, Daniele Venturi
Intent Engine is a natural‑language intent translation architecture that converts user intents into validated Service‑level Objectives (SLOs) for compute‑continuum microservice placement. It combines schema‑constrained extraction, retrieval‑grounded value construction from monitored infrastructure, and validation against supported constraints to produce reliable SLO artifacts. In evaluations on a 716‑record dataset, Intent Engine outperformed prompting baselines and a rule‑based parser, achieving a 0.941 total F1 score with GPT‑4.1 mini and reducing downstream placement failures from 30.8% to 2.1%.
By Koushikur Islam, Rodrigo N. Calheiros
arXiv:2608.21247v1 Announce Type: new
Abstract: Token compression has become a key technique for reducing the inference cost of large foundation models, with approaches such as token pruning and KV-c...
By Zhuoyuan Li, Rui Zhao, Jin Wang, Hanwei Zhu, Cong Zhang, Giuseppe Valenzise, Weisi Lin, Kin-Man Lam
The article reviews how multimodal large language models (MLLMs) are expanding radiology AI beyond image‑specific tasks to multimodal reasoning, yet volumetric radiology poses a representational challenge because clinical interpretation needs full 3‑D spatial context and quantitative data. It surveys over 200 studies, categorizing advances in volumetric representation, multimodal understanding, and agentic orchestration, and introduces a Claim‑Design‑Validation framework to align technical, workflow, and clinical claims. The review emphasizes that native volumetric modeling and agentic capabilities must match spatial, quantitative, contextual, and workflow demands, and that clinical credibility hinges on faithful 3‑D representation, traceable behavior, proper validation, and defined human oversight.
By Zanting Ye, Shengyuan Liu, Xin Liu, Chenhui Wang, Zhisong Wang, Jiashuai Liu, Zipei Wang, Cheng Wang, Wentao Pan, Mengjie Fang, Di Dong, Mohammad Salmanpour, Arman Rahmim, Yu Gu, Yong Xia, Hongming Shan, Yixuan Yuan, Yefeng Zheng, Lijun Lu
The paper investigates two strategies for improving large language model (LLM) evaluation: specialized judge weights and rule‑based deferral policies. Experiments on nearly 100,000 rubric‑conditioned samples show that correct rubrics boost accuracy, while incorrect ones hurt it, and that splitting training data into criterion‑specific experts can severely degrade performance unless the experts are warm‑started from a unified model. The authors demonstrate that lightweight deferral cascades can match or exceed the accuracy of larger standalone judges at a fraction of the compute cost, and they provide practical design rules for building efficient, reliable LLM evaluators.
By Ye Chen, Weining Zhang