Grounded Adjudication of Variations across Extracted TimeLines (GAVEL) is a new LLM‑based protocol that compares two clinical timelines against their source case report, identifying discrepancy types, issuing verdicts, and citing relevant report passages for each difference. In a study of 126 reports, GAVEL evaluated 2,738 findings from GPT‑5.6sol and DeepSeek V3.2, ranked six LLM extractors and two human annotators, and guided a merging process that improved timeline accuracy—reducing discrepancies from 7.63 to 0.85 per report and yielding a 77.0% preference rate for merged timelines. The approach demonstrates that report‑based comparison can refine extracted timelines without assuming any single timeline as ground truth.
By Jack Cummins, Sayantan Kumar, Ketan Tamirisa, Jeremy C. Weiss
The paper presents a carbon‑aware routing framework for function‑calling in large language models that distributes queries across a three‑tier edge‑cloud architecture. A lightweight k‑NN predictor estimates accuracy, delay, and power for each edge tier, and real‑time grid carbon intensity is used to route queries to the lowest‑emission tier that can execute them. Experiments on state‑of‑the‑art benchmarks show the framework matches cloud‑level accuracy while cutting operational carbon emissions by an average of four times.
By Aikaterini Maria Panteleaki, Varatheepan Paramanayakam, Spyros Tragoudas, Iraklis Anagnostopoulos
FLoKD is an adaptive knowledge‑distillation framework designed for federated fine‑tuning of low‑rank LLMs over wireless networks. It transmits intermediate LoRA activations instead of full parameters or token‑level logits, and uses transformer block importance scoring plus dataset selection to reduce communication. Experiments on WikiText‑103, PTB, and Dialog show a 50‑65% reduction in communication while maintaining competitive perplexity.
By Xinlu Zhang, Na Yan, Yang Su, Yansha Deng, Toktam Mahmoodi
The paper presents a method for fine‑tuning a large language model (LLM) recommender to generate personalized, non‑harmful explanations for its recommendations. By training two LLM‑judge reward models and using constrained GRPO, the authors achieve a significant increase in the PASS rate for all three criteria, from 0.649 to 0.956 on their own judges and from 0.677 to 0.931 on an independent judge. The fine‑tuned model maintains its original recommendation performance, demonstrating that LLM‑based recommenders can be adapted to complex tasks without loss of effectiveness.
By Jiashu He, Emma Yanyang Kong, JJ Tan, David Fagnan
The paper introduces MACE, a Multi-Agent Candidate Event acquisition method designed to improve event linking by refining event structure before the linking step. MACE employs evidence-specialized large language model agents to gather time, location, participant, and event-type evidence, exposes intermediate queries to candidate-event lookup tools, and allows a coordinator to revise the evidence set before final candidate construction. Experiments on two event linking benchmarks demonstrate that integrating MACE consistently boosts accuracy across different event linking models without altering the underlying models.
By Ziyang Zhang, Yinan Liu, Boyi Xue, Yingxuan Huang, Bin Wang, Xiaochun Yang
The paper introduces a self-demonstration-driven method for mapping relational database schemas to ontologies, addressing challenges such as semantic heterogeneity and cryptic schema naming. It combines neuro-symbolic task decomposition with pattern-guided, dependency-aware demonstrations to improve LLM performance on schema-ontology mapping. Experiments on the RODI benchmark show state‑of‑the‑art results, outperforming existing methods by up to 25 percentage points in F1 score.
By Siddhesh Thombre, Manasi Patwardhan, Sunita Sarawagi
The paper introduces a Large Language Model–enhanced Multi-Agent Reinforcement Learning framework for optimizing electric vehicle charging, station profitability, and grid stability in public charging systems. By using an LLM to select interpretable features from IoT data and dynamically balance conflicting objectives, the approach unifies grid, EV, and station optimization in a single loop. Experiments show the method outperforms existing baselines, improving market efficiency and cutting training time by more than 70%.
By Yang Zhang, Lindong Xie, Chongyu Wang, Gaojunjie Li, Siqi Bu, Edward Chung
The paper proposes a framework for delineating how acquired representations expand a system’s cognitive repertoire without necessarily transferring the underlying capacities used to create them. It introduces a five-part attribution table—effective tracking, application of acquired structures, acquisition from explicit specifications, acquisition from identifying observations, and retention and reuse—to specify the limits of this enlargement. The framework is applied to examples such as Andrew Ng’s world‑model interpretation of Othello‑GPT and contemporary machine‑concept accounts, illustrating that even full application competence does not guarantee acquisition capacity and that acquiring a criterion from its description differs from finding it in examples.
By Yiling Wu
The paper presents a study on fine‑tuning open‑source instruction‑tuned language models for a Linear Control Systems course using LoRA. A dataset of 360 system‑user‑assistant conversations was created, and LoRA was applied to Qwen2.5‑3B‑Instruct and Qwen2.5‑7B‑Instruct with ranks r=4, 8, and 16. Evaluation with ROUGE, BERTScore, and structured‑output metrics showed that LoRA improved similarity and stability, with the 7B‑r16 model achieving the highest scores and r=8 offering a good trade‑off between performance and parameter efficiency.
By Shaowen Lu, Chengxu Liu, Ping Zhou, Tao Yang
The paper presents a transformer-based framework for detecting schizophrenia from EEG signals. It converts preprocessed EEG recordings into spectrograms via Short-Time Fourier Transform and classifies them using both traditional machine learning algorithms and deep learning models, including CNN-Transformer hybrids. Subject-level data partitioning ensures reliable evaluation, yielding an AUC-ROC of 88.41% for the CNN-Transformer model and 92.88% for the CNN + Squeeze and Excitation + Transformer model on an independent test set.
By Abtin Shafiei, Mohsen Hooshmand, Majid Ramezani
MOSCOPT is a parameter‑free algorithm that jointly optimizes a pool of N skills and a gating skill G, which dynamically selects K skills at each step for LLM agents. It introduces EditAdam, a dual‑state optimizer, and a three‑phase interleaved update scheme that monotonically improves performance without gradient or parameter tuning. Experiments on five benchmarks and three target LLMs show MOSCOPT consistently outperforms baselines, highlighting the importance of mixture‑of‑skills architecture and collective evolution.
By Zhenyu Zhang1, Jiudong Yang
VeriDx is a disease‑centric verification framework that links free‑form diagnostic reasoning to structured disease profiles, tracking whether each hypothesis satisfies, remains unresolved, or violates its clinical obligations. It exposes failures such as missing critical tests, unresolved differentials, ignored contradictions, unsupported claims, and premature closure. Applied to complex respiratory diagnosis, VeriDx reveals that many diagnostic errors stem from broken commitments made earlier in the reasoning process.
By Zhong Cao, Shuying Chen
The paper presents a method for generating lower‑limb joint‑angle gait trajectories using conditional diffusion models. It compares a baseline transformer diffusion model with a controllable diffusion transformer that includes adaptive normalization and classifier‑free guidance. Experiments on 4,590 gait cycles demonstrate that these diffusion models can produce realistic, periodic gait patterns while allowing some control over gait characteristics such as step length.
By Damian Benasco, Juan Carballeira-Lopez, Jaime Ramos-Rojas, Julio S. Lora-Millan, Antonio J. Del-Ama, David Rodriguez-Cianca, Pablo Lanillos
The paper introduces a Bayesian framework for assessing intelligence in agents such as language models. It shows that an agent’s reports are consistent with Bayesian intelligence if they are not fully contradictory across prompts, and it defines an intelligence order based on the informativeness of internal experiments. The work also demonstrates the challenges of aggregating coarse reports from intelligent agents, revealing that optimal aggregation can assign arbitrary weights to unexcluded states unless the agent reports a belief about the complete state of the world.
By Alex Smolin, Bryan Wilder
AcquireBound is a runtime authorization framework that ensures AI agents can safely acquire and activate resources such as compute, credentials, and services. It quarantines acquired outputs, resolves their capabilities through authenticated evidence, and activates them only after verifying a manifest, provenance, and relational constraints. The system demonstrates strong safety properties, passing extensive benign and unsafe trace tests across multiple resource classes.
By Genliang Zhu
The paper introduces CLEAR, a CLoze-style rEAsoning-based Re-ranking framework for Compositional Zero-Shot Learning. CLEAR treats primitive variations as context-driven activations of concrete visual cues rather than independent entities, extracting conditional variants in a coarse-to-fine manner and performing cloze-style reasoning to infer high-level semantics. Experiments show that CLEAR consistently improves base models and surpasses state-of-the-art methods on the C-GQA and MIT-States datasets.
By Weize Li, Zhicheng Zhao, Fei Su
The paper presents a method for creating and manipulating causal virtual worlds using large-language-model (LLM) and large-video-model agents guided by feedback fuzzy cognitive maps (FCMs). It extracts dynamical meta‑rules of the form "If A then B" from the FCM, has an LLM write a script based on these rules, and then uses a large video generator to render the resulting causal scenes. The authors demonstrate the approach on a simple undersea world of dolphins and sharks, showing that the system can scale to larger FCMs and more immersive virtual worlds.
By Akash Kumar Panda, Olaoluwa Adigun, Bart Kosko
Guardrail models, which screen malicious prompts in LLM services, often use lightweight Transformers with short context windows and bucketed positional encodings. The study identifies a new failure mode called Overflip, where repeating a prompt causes the guardrail’s prediction to flip from malicious to benign as the sequence length increases. Experiments on nine popular guardrails show that 5 models exhibit MAL→BEN flips on 100 prompts, with flip rates ranging from 8% to 92% and first flips occurring between 2.6k and 9.4k tokens, highlighting a gradual attention dispersion distinct from traditional attention‑dilution attacks.
By Xu He, Chih-Hsuan Lin, Hung-Mao Chen, Junjie Xiong, Yan Zhai, Kun Sun
The paper introduces a new inference architecture for vibe design agents that separates design exploration from implementation. By generating structured design specifications with typicality scores and selecting one for downstream generation, the method allows users to explore coherent UI alternatives without altering the underlying generation settings. Experiments on UI themes and visual-asset prompts show increased selection coverage and screenshot variation, with mixed preferences from an LLM judge and modest operational costs in a large online test.
By Yifan Zhang, Nghi D. Q. Bui, Georgios Evangelopoulos, Arnaud Benard
The paper presents MediClear, an LLM-based system that simplifies diabetes-related medical information for patients. By indexing public articles from Diabetes Australia, WHO, ADA, NIDDK, and AIHW in a Retrieval-Augmented Generation knowledge base, MediClear retrieves clinically grounded content and rewrites it into patient-friendly language. Evaluation shows the system consistently lowers reading levels to the recommended patient literacy range and receives high user satisfaction in a human study.
By Pallika Kafle, Yipeng Zhou, Guanfeng Liu, Quan Z. Sheng, Cheng-Hsin Hsu