The paper introduces SGMA, a structure‑guided masked autoencoding framework designed for ultra‑high‑resolution scientific images. SGMA combines a content‑adaptive quadtree tokenizer that reduces gigapixel images to a fixed‑length sequence with a structure‑conditioned masking process that focuses reconstruction on spatially informative regions. The method, enhanced by Damped Accumulation to stabilize multi‑scale signals, achieves superior performance over standard MAE baselines on electron microscopy, whole‑slide optical microscopy, and X‑ray CT datasets, delivering significant accuracy gains and up to a 24.8× inference speedup.
By Enzhi Zhang, Du Wu, Rui Zhong, Cong Ma, Isaac Lyngaas, Amir Koushyar Ziabari, Xiao Wang, Peng Chen, Tao Luo, Toshio Endo, Fumiyoshi Shoji, Kento Sato, Kentaro Uesugi, Takayuki Nonoyama, Ryuji Kiyama, Masahiro Yoshida, Masaru Tezuka, Tetsuya Ishikawa, Satoshi Matsuoka, Masaharu Munetomo, Mohamed Wahib
The paper introduces Auto-Comp, a fully automated, concept-driven pipeline that generates photorealistic compositional benchmarks for vision‑language models. Auto‑Comp creates paired Minimal and Contextual samples for each concept, enabling isolation of core binding abilities from visio‑linguistic complexity. Evaluations across 25 models reveal consistent failures in attribute and relational binding, with context helping relational tasks but hindering attribute tasks due to visual clutter.
By Cristian Sbrolli, Toshihiko Yamasaki, Matteo Matteucci
Self-Play Search Distillation (SPSD) is a framework that generates superhuman synthetic data by having MuZero-like networks play board games in executable environments. The search records are converted into structured reasoning chains that serve as environment‑grounded supervision for training large language models. When applied to Qwen3‑4B‑Base, SPSD improves performance on six mathematics benchmarks from 24.1 to 36.6 and raises the win rate on unseen games from 15% to 45%.
By Lorenzo Molfetta, Wai-Chung Kwan, Giacomo Frisoni, Luca Ragazzi, Gianluca Moro, Pavlos Vougiouklis, Jeff Z. Pan, Pasquale Minervini
The paper "Financial Fragility in Societies of LLM Agents: Coordination Failures and Stabilizing Mechanisms" investigates how large language model agents can collectively cause financial failures when making individual protective decisions. Using the FRAIL framework, the authors simulate bank runs, debt rollovers, and reward crowdfunding, finding that 77% of bank-run and 83% of debt-rollover episodes fail even without malicious agents. They test three interaction mechanisms—compensated commitments, centralized agreements, and participant-led coalitions—each improving outcomes but none dominating across all scenarios, noting that early broad commitments are key to successful stabilization.
By Zhenhao Fu, Ruipeng Xu, Qibing Ren
The paper introduces mutable transcripts, an interaction paradigm that lets users edit prior turns in a chat, turning the conversation history into an editable state rather than a fixed record. A prototype was built and tested with 17 participants, who preferred mutable transcripts over standard chat for clarity, confidence, and ease of use, and reported less need to restart conversations. Analysis of user study transcripts shows that mutable transcripts can shorten conversations and remove outdated context, suggesting that user-driven revisions improve interaction quality.
By Dan Barry, Andrew Hines
Cartograph is a federated Model Context Protocol (MCP) proxy that reduces AI agent tool discovery from linear catalog traversal to progressive disclosure, exposing only a few proxy tools instead of all definitions. It uses operator-attested capability cards, a three-layer confusable-cluster analysis called Rift, and a two-stage retrieval process to rank servers before tools. In a 22-server, 374-tool deployment, Cartograph achieves higher recall (R@5 = 0.816 vs. 0.592) and drastically fewer tokens (475 vs. 42,450) for discovery exchanges, with minimal latency overhead.
By Justice Owusu Agyemang, Michael Agyare, Kwame Opuni-Boachie Obour Agyekum, Kwame Agyeman-Prempeh Agyekum, Francisca Adoma Acheampong, Jerry John Kponyo
CARGO is a framework for evaluating agentic AI systems in production that addresses the problem of reference-instance divergence (RID), where reference-based judges penalize correct answers that involve different entity identifiers. It treats retrieved references as procedural exemplars, grounds judgments in the live instance’s context, assigns a three-way status to claims, and gates evaluation by retrieval confidence. Using the CARGO-Bench diagnostic suite, CARGO eliminates false penalties and improves discrimination while revealing a limitation in detecting procedural corruptions.
By Mukul Chhabra, Shail Patel, Luigi Medrano
The paper proposes Metric-based Loss Weighting to enhance visual grounding in multimodal machine translation. By increasing loss for tokens that benefit from image context—identified via the Point-wise Cross-mutual Information (PCXMI) metric and its Congruency-based variant—the method improves translation accuracy on the CoMMuTE dataset by over 7 percentage points. Experiments fine-tune three pretrained multimodal LLMs across three language directions, showing superior performance compared to standard fine-tuning while preserving overall translation quality.
By Pawe{\l} M\k{a}ka, Piotr Andruszkiewicz, Yusuf Can Semerci, Jan Scholtes, Gerasimos Spanakis
The paper introduces a blockchain-backed agentic security framework that protects the entire software development lifecycle and the AI components monitoring it. It coordinates specialized security agents—covering source integrity, dependency and SBOM analysis, CI configuration auditing, artifact verification, and runtime policy evaluation—each powered by a large language model that interprets artifacts, reasons over tool outputs, and generates structured security reports. Every agent produces a cryptographically signed attestation recorded on a permissioned blockchain via smart contracts, creating an immutable attestation log, an agent registry, and an enforceable release‑policy module, while communication is secured through a consortium‑operated certificate authority.
By Toqeer Ali Syed, Asadullah Abdullah Khan
ViSTA is a lightweight adapter that adds irregular numerical measurements to a pretrained vision‑language model’s chart representations, enabling accurate clinical time‑series prediction without altering the base model’s parameters. On the MIMIC‑IV dataset, ViSTA outperforms other adaptations across four metrics for acute kidney injury and mortality prediction, achieving an AUC of 0.7376 with only 0.516 million trainable parameters. It also delivers strong temporal question‑answering performance, reaching 69.27% accuracy with significantly fewer trainable parameters than low‑rank adaptation methods.
By Junyi Gao, Yu Shi, Pingzhao Hu, Ewen M Harrison
arXiv:2609. 31450v1 Announce Type: cross Abstract: Medical vision-language model (VLM) post-training is commonly evaluated through answer accuracy.
By Wang Jingxin
The paper "Can You Check That? The Checkability Boundary for Local LLM Network Automation" proposes a method called Touchstone that uses local small language models (SLMs) to generate network‑automation candidates and applies task‑specific intrinsic checks to reject incorrect outputs before escalating to a larger frontier LLM. By defining a task as checkable when a cheap, deterministic test can reject outputs violating a necessary correctness condition, the authors demonstrate that Touchstone achieves high end‑to‑end accuracy (98.6% on conflict detection and 93.8% on intent translation) while escalating only a small fraction of inputs. The study shows that local inference is preferable when precise, low‑cost checks are available, whereas tasks lacking such checks should rely on the frontier model.
By Maleeha Masood, Momina Nofal
The paper examines how evaluation design can cause significant fluctuations in the benchmark results of reasoning models, particularly the Deepseek‑R1‑Distill series. It shows that subtle changes in evaluation conditions lead to large variations in reported performance, a phenomenon also seen in other open‑source models fine‑tuned from Deepseek‑R1‑Distill and in the QwQ‑32B model. The authors call for a more rigorous evaluation paradigm and provide empirical assessments of the Deepseek‑R1‑Distill models.
By Yongfu Zhu, Lin Sun, Jinzhu Wu, Weihong Lin, Xiaoqi Jian, Guangxiang Zhao, Change Jia, Linglin Zhang, Sai-er Hu, Yuhan Wu, Xiangzheng Zhang
The paper introduces AttriBench, a benchmark dataset that balances author fame and demographics to study quote attribution in large language models (LLMs). Using AttriBench, the authors evaluate 11 popular LLMs and find that accurate attribution remains difficult, with significant disparities across race, gender, and intersectional groups. They also identify a new failure mode—suppression—where models omit attribution entirely, which is unevenly distributed across demographics and not reflected by standard accuracy metrics.
By Eliza Berman, Bella Chang, Daniel B. Neill, Emily Black
The paper introduces TokenAdapt, a model‑agnostic tokenizer transplantation method that uses a hybrid heuristic to initialize new token embeddings, and a novel pre‑tokenization learning approach for multi‑word Supertokens to improve compression. TokenAdapt combines local subword decomposition and global semantic similarity to preserve semantics while reducing retraining needs. Empirical results show that TokenAdapt outperforms existing baselines such as Transtokenizer and ReTok, achieving lower perplexity ratios and significant compression gains.
By Shaurya Sharthak, Vinayak Pahalwan, Adithya Kamath, Adarsh Shirawalmath
SLMFix is a code‑generation pipeline that uses a small language model fine‑tuned with reinforcement learning to correct syntactic errors in programs produced by large language models for domain‑specific languages. The approach relies on interpreter feedback to guide the error‑fixing process. Experiments show that SLMFix improves validator pass rates by 40% on low‑resource programming languages and removes over 50% of syntactic errors on high‑resource DSLs, outperforming supervised fine‑tuning even for 7B models.
By David Jiahao Fu, Aryan Gupta, Aaron Councilman, Yu-Xiong Wang, Vikram Adve
The Digital Consciousness Model (DCM) is introduced as a systematic, probabilistic framework for evaluating evidence of consciousness in AI systems, drawing on multiple leading theories of consciousness. Initial results indicate that, while the evidence suggests 2024 large language models (LLMs) are not conscious, this conclusion is not decisive and is weaker than evidence against consciousness in simpler AI systems.
By Derek Shiller, Laura Duffy, Arvo Mu\~noz Mor\'an, Adri\`a Moret, Chris Percy, Hayley Clatterbuck
The paper introduces CaC, a coarse‑to‑fine anomaly reward model that uses Vision‑Language Models to first scan globally for anomalous time windows, then ground anomalies spatially, and finally reason with structured spatiotemporal Chain‑of‑Thought. It builds the first large‑scale generated video anomaly dataset with detailed annotations and trains the model through a three‑stage progressive paradigm, including reinforcement learning with Group Relative Policy Optimization. Experiments show CaC improves fine‑grained anomaly detection by 25.7% and reduces generated‑video anomalies by 11.7% while enhancing overall video quality.
By Jiyuan Wang, Huan Ouyang, Jiuzhou Lin, Chunyu Lin, Dewen Fan, Boheng Zhang, Haonan Fan, Honglie Wang, Yiyang Fan, Zhenlong Yuan, Zijun Li, Yongrui Heng, Guosheng Lin, Fan Yang
The paper introduces PromptCCZSL, a framework that enables vision‑language models to continually learn new attributes, objects, and their unique compositions while avoiding forgetting. It uses a frozen VLM backbone with prompt‑based techniques, recency‑weighted multi‑teacher distillation, and several loss functions (CAL, OPL, IDL) to maintain prior knowledge and promote diverse, distinct embeddings. Experiments on UT‑Zappos and C‑GQA show significant performance gains over existing VLM‑based and non‑VLM baselines, establishing a new benchmark for continual compositional zero‑shot learning.
By Sauda Maryam, Sara Nadeem, Faisal Qureshi, Mohsen Ali
The paper evaluates a production text‑to‑SQL pipeline that uses an LLM as a judge, finding that the deployed gpt‑4o‑mini judge agrees with human annotators only weakly (Cohen’s kappa 0.04 on a disagreement‑enriched set and 0.42 on a random spot‑check). The authors identify a specific failure mode, GRADE‑HALLUCINATION, responsible for most over‑flags, and demonstrate that a self‑hosted Qwen3.6‑27B model achieves substantially higher agreement (kappa 0.72) at a much lower cost. They also show that ensembling judges does not improve performance, and that their audit method flags a significant portion of out‑of‑domain SQLs as potential issues.
By Haowei Liu, Hsin-Tai Wu, Yi Fang