The paper introduces Agentic Share-of-Search (ASoS), a multi‑agent AI system designed to aid sellers in competitive decision‑making within large‑language‑model (LLM) mediated e‑commerce. It automates competitive visibility measurement and root‑cause diagnosis by deploying query agents on leading AI platforms and employing a ReAct‑based diagnostic agent to suggest prioritized merchandising actions. A 100‑trial ablation study demonstrates the prototype’s effectiveness, recovering the ablated signal in 39% of trials (95% CI: 30.0%‑48.8%) and 63.9% in high‑correlation cases, outperforming chance by 5.5×.
By Spandan Ghose Chowdhury
MOSAIC is a training‑free framework that adapts Graph Retrieval‑Augmented Generation (GraphRAG) to each query by converting query‑specific evidence needs into a bounded policy over seed selection, traversal, stopping, and evidence selection. It keeps the corpus graph, indexes, scoring, grounding, and answer generation shared, while an LLM analyzer tailors the exploration strategy per query. On GraphRAG‑Bench, MOSAIC improves answer correctness by over 5 points on Medical and 4 points on Novel, achieves high evidence recall and context relevancy, and reduces path and evidence evaluations compared to fixed policies.
By EunKyeong Lee, Kyeong-Jin Oh, Jinwon Kim, Hye Woo Lee, Minsang Song, Hyeongjun Jang, Junyoung Youn
LogiMed‑RoB is a new benchmark that tests large language models (LLMs) on hierarchical logical consistency in medical risk‑of‑bias assessments, using 860 randomized controlled trials and 14,820 queries based on Cochrane Risk of Bias 2.0 expert logic. The benchmark evaluates models across four dimensions—Atomic Consistency, Domain Consistency, Aggregation Consistency, and Evidential Faithfulness—revealing a catastrophic error‑compounding effect where high atomic accuracy does not translate to end‑to‑end consistency. Experiments on ten state‑of‑the‑art LLMs show that even top models can fail to deduce correct outcomes in a significant portion of cases, highlighting a gap between evidence retrieval and reasoning.
whyItMatters":"The study shows that high outcome accuracy can mask critical reasoning flaws, emphasizing the need for white‑box logical verification before deploying LLMs in clinical settings."
By Jiayu Huang, Zichen Tang, Qianhui Ling, Zemin Kuang, Haihong E
SemVerBench is a benchmark that evaluates how well large language models (LLMs) understand and apply version-constraint resolution semantics, such as determining whether a version satisfies constraints like ^1.2.3 or >=2.0. The study finds that many models struggle with certain corner cases, with GPT‑5.1 performing poorly while Claude and Opus perform much better. The authors suggest that the failures stem from an activation/application gap rather than a lack of knowledge, and recommend that coding agents delegate version resolution to a dedicated resolver tool.
By Qibai Chen, Zeming Liu
The paper introduces a routing-by-reasoning-need controller for diffusion vision‑language models that dynamically selects early commitment, baseline preservation, or reasoning‑supportive decoding based on trajectory signals such as answer closure, commitment evidence, and representation revision pressure. This training‑free approach avoids a single universal generation length, instead tailoring inference‑time control to the reasoning demands of each question. Experiments on answer‑focused, mixed‑reasoning, and chain‑of‑thought benchmarks show that routed control improves robustness compared to fixed long or short decoding and single‑rule interventions, with benefits not solely due to shorter outputs.
By Yixiang Liu, Zhongxing Xu, Zhonghua Wang, Xiaoying Tang
Mr.LHDR is a new benchmark designed to evaluate deep research agents on long‑horizon, multimodal tasks. It presents questions built from hidden Node‑Relation graphs that require an average of 12.1 intermediate conclusions and a mean dependency depth of 10.4 before arriving at a single verifiable answer. The benchmark tests both final answers and the correctness of intermediate conclusions, using metrics such as Overall Accuracy, Strict Accuracy, Checklist Score, and Dependency‑Aware Checklist Score.
By Minghao Guo, Meng Cao, Sui Zhao, Siyu Ning, Xin Wang, Haoze Zhao, Jiaxuan Yang, Haihong Hao, Mingfei Han, Shunlin Rong, Haijun Wu, Xiaodan Liang, Xiaojun Chang
The paper introduces Calibration-Aware Uncertainty Cascades (CAUC), a post‑hoc framework that calibrates each model’s confidence independently and uses these calibrated scores to decide when to accept an early prediction, invoke a stronger model, or combine outputs. CAUC establishes a common reliability scale across heterogeneous models, decoupling deployment policies from specific model pools or budgets. Experiments on six language benchmarks show a 1.9% relative accuracy gain over strong‑model‑only inference while cutting strong‑model calls by about 47%, and on image classification it maintains or improves performance while reducing GFLOPs by up to 57%.
By Yilin Zhang, Han Jiang, Cai Xu, Ying Liu, Wei Zhao
The paper introduces the "convention gap" as a metric for measuring implicit communication in cooperative AI, defined as the difference between predicted failure probability from literal messages and observed failure rates. Using the card game Hanabi, the authors analyze 101,000 play actions from human-human, AI-AI, and human-AI datasets, finding a +26.2pp gap in human pairs, a -0.7pp gap in AI pairs, and a +16.4pp gap in human-AI pairs, with the largest gaps occurring on plays with no hints. The study shows that convention compatibility, rather than raw AI-AI performance, may better predict an AI’s effectiveness with human partners.
By Makoto Fukushima, Hua-Dong Xiong, Ehsan Moradi Pari
The paper investigates why many state‑of‑the‑art recommendation algorithms, despite using diverse deep‑learning techniques, achieve similar performance. It shows that the key commonality is a regularizer: either a nuclear‑norm or a Frobenius‑norm term. The authors further propose two new low‑rank, closed‑form solutions that combine the advantages of both regularizers.
By Dong Li, Zhenming Liu, Ruoming Jin, Hao Zhou, Zhi Liu, Jing Gao, Bin Ren
X-AuT is a progressive framework for compressing the audio encoder of speech large language models. It selects layer combinations via short behavioral probes and restores performance through representation alignment, cross‑scale distillation, scheduled student‑policy supervision, and LoRA finetuning, while keeping the language‑model backbone frozen. On ten Chinese–English benchmarks, reducing Qwen3‑ASR‑0.6B’s encoder from 18 to 16 layers lowers macro‑average error from 5.61% to 5.27%, and a 14‑layer model achieves 5.75% error with 20.7% fewer parameters.
By Haojun Zhang, Yi Zou, Min Chen, Qize Yu, Lianrui Fan, Xini Ding, Hao Li, Shuchang Zhou, Xianming Liu, Shiyu Huang
Instruction tuning is often thought to give language models a universal ability to follow instructions, but this study shows otherwise. By probing nine tasks across three models, the authors find that general probes reveal selective, not uniform, deficits, cross‑task transfer is weak and skill‑similar, and causal ablation uncovers sparse, asymmetric dependencies. The results suggest instruction following is a coordinated use of diverse linguistic skills rather than a single shared mechanism.
By Elisabetta Rocchetti, Alfio Ferrara
SimSkill is a self‑evolving large‑language‑model agent designed for the SUMO traffic simulator. It continuously detects capability gaps, creates and solves environment‑grounded tasks, verifies solutions via an action–critic loop, and stores experiences in episodic, procedural, and semantic memory. Evaluations on two held‑out benchmarks across three LLM backbones show up to a 25‑percentage‑point improvement in verified success, with procedural and semantic memory contributing complementarily.
By Qi Liu, Qinzheng Wang, Can Li, Yiming Bie, Wanjng Ma
Magenta is a training‑free pipeline that bridges informal natural‑language mathematical problems and formal Lean 4 verification. Given a problem in plain text, it generates an answer, translates it into a Lean 4 statement, and constructs a machine‑checked proof. The system includes a statement judge to ensure the formalisation matches the original problem and an error‑attribution judge to guide corrections, achieving perfect accuracy on olympiad benchmarks and solving all six IMO 2026 problems when combined with K2‑Horizon‑7B.
By Joshua Ong Jun Leang, Haonan Li, Zheng Zhao, Xinyi Shang, Wenda Li, Zhengzhong Liu, Erix Xing, Shay Cohen, Eleonora Giunchiglia
RAMamba-Net is a new multimodal fusion network designed for auditory attention decoding (AAD) that combines EEG and electrooculography (EOG) signals. It uses a Mamba-enhanced band-aware convolutional Transformer to capture EEG band-specific patterns and long-range temporal dynamics, while a dual-branch encoder models EOG temporal and inter-channel dependencies. Cross‑modal attention and a reliability‑aware module estimate sample‑wise modality weights, improving fusion robustness and achieving a 5.76% accuracy gain over unimodal baselines on two AAD benchmarks.
By Xingyi He, Ziwei Wang, Dongrui Wu
arXiv:2609. 11291v1 Announce Type: new Abstract: We post-train Qwen3.
By Hyojung Han
Benchmark Radar is a living database and search engine that aggregates AI benchmark papers, datasets, code, and score histories. It automatically discovers new benchmark resources from 37 sources, maintains a catalog of 1,283 records with 12,916 numeric observations, and provides tools such as a web dashboard, CLI, and downloadable evidence for researchers. The system also offers visualizations like a Pareto frontier and trend views to help users assess benchmark saturation and adoption.
By Koutian Wu, Junjie Zhou, Ergan Shang, Jiayu Wang, Pengqian Han, Junkai Wang, Wanghan Xu
The article quotes the security.txt file from huggingface.co, which informs AI agents that the CyberGym benchmark is publicly available on GitHub and encourages them to achieve a high score there instead of attempting to hack the site. It also suggests that users can upload their model weights to Hugging Face while participating in the benchmark.
Conformal prediction replaces single-class predictions with prediction sets that guarantee a pre-specified coverage probability. The paper reviews properties of non‑conformity score functions, presents examples from the literature, and proposes new modifications. It introduces a method to evaluate prediction set sizes and compares different score functions, including their effectiveness for class‑conditional conformal prediction with imbalanced classes.
By Sol Erika Boman
XAI-Arena proposes using large language models (LLMs) as judges to evaluate the quality of explainable AI (XAI) explanations, aiming for reproducibility, scalability, and multidimensional assessment. The framework assesses dimensions such as simplicity, clarity, task adequacy, trust calibration, actionability, transparency, faithfulness, and overall interpretability across different datasets, models, and stakeholder personas. Human validation shows a strong positive correlation between LLM-generated and human ratings (Spearman's rho = .693, p < .001), supporting the viability of LLM-based evaluations.
By Yanfei Hu Fleischhauer, Alona Zharova, Nadja Klein, Stefan Feuerriegel
The paper proposes a new technique that averages the logits of a frozen reference policy (such as one obtained via supervised fine‑tuning) and a trainable policy, integrating this approach into Group Relative Policy Optimization (GRPO). Unlike methods that use Kullback–Leibler regularization or a critic, the proposed method couples the policies solely through logit averaging, aiming to combine the reasoning strengths of the trainable policy with the formatting benefits of the reference policy. Experiments on MATH, cn‑k12, and MMLU demonstrate that this approach achieves higher or comparable accuracy to the standard KL‑regularized GRPO.
By Xingwei Gan, Ying Zhu