The paper introduces RareTrap, a framework that estimates the probability of severe behaviors in black‑box large language models. RareTrap constructs a geometry‑aware mapping from a low‑dimensional latent space into token‑embedding space using a surrogate LLM, creating an explicit and reproducible distribution over input prompts. By applying a response‑level performance function and sequential rare‑event simulation, RareTrap concentrates evaluations on increasingly severe behaviors while preserving probability, enabling estimation of such behaviors with as few as 200 evaluations across multiple open‑weight and frontier models.
By Elsayed Eshra, Ali Al-Lawati, Dongwon Lee, Suhang Wang
The paper introduces Knowledge-Aware Semantic Bridging (KASB), a framework designed to improve Retrieval-Augmented Generation (RAG) by aligning the semantic spaces of queries and retrieved contexts. KASB achieves this through intelligent fusion of generative and retrieval-based knowledge in a multistage process, aiming to enhance passage selection quality, relevance, and accuracy. The authors evaluate the method on three popular open-domain Question Answering datasets, demonstrating its effectiveness.
By Xinkai Du, Chao Lv, Yalin Sun, Quanjie Han, Lei Yao, Maosong Sun
The paper introduces SCSP, a training‑free framework that improves long‑context embeddings by selectively pooling informative tokens. SCSP partitions documents into sentence‑aware chunks, adds a semantic compression prompt to each chunk, and uses prompt‑isolated attention masks to estimate token importance. The selected tokens’ intermediate‑layer representations are aggregated to form the final embedding, yielding consistent performance gains across zero‑shot and fine‑tuned models on long‑context benchmarks.
By Zifeng Cheng, Jie Zheng, Zhiwei Jiang, Shuwen Wang, Fei Shen, Shiping Ge, Qing Gu
The paper introduces WINGS, a reference‑free Gaussian splatting inpainting technique that operates directly in 3D. It uses a large, pre‑trained 3D generative prior and a structure completion network to reconstruct missing geometry and appearance without generating reference views. The method claims faster performance and reduced multi‑view inconsistency compared to 2D diffusion‑based approaches, and its effectiveness is validated through experiments and a user study.
By No\'e Lallouet, Michael Fischer, Elie Michel
arXiv:2608.25466v2 Announce Type: replace-cross
Abstract: The functional annotation of genes in non-model organisms remains a significant challenge in computational biology, with 20-70% of sequenced...
By Azrin Sultana
AdaTutoRank introduces a setwise document reranker that uses Adaptive Tutoring Optimization (ATO) to provide graded supervision across nine rubric dimensions. By generating hint‑based silver labels, reinforcement rewards, and distillation cues tailored to each rollout’s quality, the method improves credit assignment for individual documents within a set. Experiments on ten benchmarks covering Retrieval‑Augmented Generation (RAG), deep research, and setwise evaluation show that AdaTutoRank achieves superior overall performance while reducing the number of retrieval calls.
By Kailin Jiang, Lei Liu, Jian Xi, Yangqi Chen, Hui Xu, Hongwei Zhao, Bin Li, Yu Lu, Haibo Shi
The paper introduces CRASM, a deterministic, constraint‑ and role‑aware semantic mapping framework for aligning engineering concepts across incompatible industrial standards, and its extension CRASM‑Gate, which optionally employs a large language model through a confidence gate while preserving deterministic validation. The framework decomposes the mapping process into standard‑specific canonicalization, bounded retrieval, deterministic rules, role interpretation, ranking, ambiguity refusal, and target validation. Experiments on 14,400 sample decisions across six standard pairs show CRASM‑Gate achieving a mean F1 of 0.9938 and perfect structural validity, outperforming a model‑only baseline and reducing latency significantly compared to generative‑model‑only approaches.
By Kabeh Mohsenzadegan, Vahid Tavakkoli, Kyandoghere Kyamakya
arXiv:2609.36890v1 Announce Type: new
Abstract: In scientific machine learning, physical fields governed by partial differential equations exhibit low-rank structure and scale invariance. When solvin...
By Kaichen Ouyang, Chenglei Yu, Chuanrui Wang, Tailin Wu
arXiv:2609.35599v2 Announce Type: replace
Abstract: When recalling lists of concepts (e.g., animals) during the semantic fluency task (SFT), both humans and large language models (LLMs) organise thei...
By Luke Leckie, Peter M. Todd, Jacob G. Foster
arXiv:2609.37435v1 Announce Type: new
Abstract: Neural Koopman autoencoder models have been shown to successfully build a latent embedding with linear dynamics for arbitrary dynamical systems, enabli...
By Anthony Frion, Lucas Drumetz, Guillaume Tochon, Mauro Dalla Mura, Ali Can Bekar, Abdeldjalil A\"issa El Bey
arXiv:2609.37884v1 Announce Type: new
Abstract: Topological structures such as simplicial complexes, hypergraphs, and cell complexes extend standard graph models by modeling higher-order relationship...
By Florian Frantzen, Ibrahem AlJabea, Ines Henriques-Cadby, Theodore Papamarkou, Mustafa Hajij, Michael T. Schaub
ThuRunel is an AI advisory agent designed for high‑stakes domains that exhibit a two‑phase interaction structure: an initial empathetic elicitation phase followed by a specialist judgment phase. It uses a finite‑state belief management framework, a chain‑of‑thought teacher synthesis protocol, and learned generation adapters to dynamically decide what to ask, when to stop, what to resolve autonomously, and what to forward to a specialist. In evaluations against eleven baselines, ThuRunel consistently improves elicitation completeness and the quality of specialist briefs, and it is publicly deployed as a bilingual web application that cites its knowledge base in every answer.
By Yuyan Chen
The paper introduces BRIDGE, a bilevel optimization framework that jointly trains a large language model (LLM) and a retriever for agentic reinforcement learning (ARL). It demonstrates that adapting the retriever before the policy yields better rewards, and that BRIDGE outperforms existing methods on seven open‑domain QA benchmarks and medical QA tasks, achieving significant gains in accuracy and reasoning quality.
By Quan Xiao, Mingda Liu, Gaowen Liu, Katsuki Fujisawa, Tianyi Chen
The paper introduces TrustSwap, a counterfactual test that swaps or removes source reliability labels while keeping evidence text constant, to evaluate how retrieval‑augmented fact‑checking models respond across verdict, confidence, and search decisions. Experiments on untrained and RL‑trained models show that confidence and search largely follow labels, yet label changes can flip a significant portion of verdicts, especially in larger models. The authors propose trust‑swap augmentation (TSA) to mitigate this shortcut, demonstrating reduced verdict flip rates and maintained accuracy in several settings, though its effectiveness diminishes at larger model scales.
By Jianchang Su, Yiwei Yang, Wei Zhang
Neural Structural Reasoner (NSR) is a brain-inspired neural network that preserves relational structure directly in the connectivity and dynamics of coupled neuronal populations. It incorporates multi-layered architecture, stable entity representations, and path integration to perform link prediction by parallelizing over candidate relational structures and using confidence-weighted scores. NSR achieves competitive accuracy on knowledge-graph benchmarks, trains faster than several neural baselines, and offers native interpretability by tracking human-readable neuron activations and extracting latent relational hierarchies and compositional rules.
By Zixing Jia, Yuhang Pan, Ni Ji
The paper introduces GeoPatch, a fixed‑scaffold patch encoder that decouples token support from signal geometry for time‑warp robust sequence retrieval. By using geometry‑derived descriptors (slope, curvature, acceleration, affine‑residual, confidence) as continuous conditioning variables, GeoPatch prevents patch boundary drift while still allowing geometry to modulate embeddings. Experiments on ECG, speech, and multivariate time‑series data show that GeoPatch improves early‑rank retrieval under timing variation and highlights a trade‑off between local surface matching and strict non‑overlap retrieval.
By Cassandra Yang, Yufan Tang
The paper introduces ImbalancE, an inference‑time latent search method that mitigates degree imbalance bias in Knowledge Graph Embedding models. It targets the problematic prediction of target entities with much lower degrees than anchor entities, a common issue in recommender systems and other applications. Experiments on benchmark datasets show that ImbalancE improves predictions on the most imbalanced triples compared to conventional methods.
By Alberto Bernardi, Luca Costabello, Christophe Gueret
arXiv:2609. 38023v1 Announce Type: new Abstract: Physics-Informed Neural Networks (PINNs) embed governing equations into deep learning, but enforce them only through loss residuals, leaving highly oscillatory wave behavior to be discovered by optimization.
By Huiwen Zhang, Feng Ye, Chu Ma
The paper introduces a structured approach to extracting skill and responsibility level pairs from free text using the Skills Framework for the Information Age (SFIA). It evaluates five methods—including lexical baselines, retrieval‑augmented generation, and multi‑agent crews—against expert‑mapped European ICT role profiles, finding that generative strategies are more precise and that only explicit level‑prediction strategies reliably assign responsibility levels. The study also releases an automated SFIA‑9 corpus and establishes the first reproducible baseline for level‑aware skill extraction.
By Ranuga Disansa, U. S. Samarasinghe, Lasith Gunawardena
TRACE is a deployable framework that enhances oncology language models by separating offline structure learning from online inference. It organizes oncology concepts and relations into an updatable tree‑relational structure, refines it with LM‑loss evidence, and retrieves compact prompt evidence during inference. The approach improves performance on ten classification tasks and a QA benchmark, outperforms vanilla RAG and generic GraphRAG, and provides interpretable evidence paths aligned with clinical reasoning.
By Jizheng Lai, Yingyun Li, Ying Qin, Haiyang Qian