arXiv:2608. 11410v1 Announce Type: new Abstract: Offline reinforcement learning (RL) offers considerable promise for optimizing ICU treatment decisions, yet standard evaluation metrics Mean Squared Error (MSE) and Fitted Q-Evaluation (FQE) assess only behavioral imitation and cannot detect Toxic Mimicry, a failure mode in which agents replicate harmful patterns such as treatment withdrawal during comfort-care transitions.
By Hangqi Ren, Junyi Liao
arXiv:2602. 17554v3 Announce Type: replace Abstract: Training large-scale generative models is resource-intensive and relies heavily on heuristic dataset weighting.
By Corinna Cortes, Mehryar Mohri, Yutao Zhong
arXiv:2608. 11242v1 Announce Type: cross Abstract: When the context window is under pressure, LLM systems compact prior context to continue ongoing tasks.
By Zhiqi Wang, Yichi Zhang, Dongwon Lee, Yuchen Yang
arXiv:2606. 16149v3 Announce Type: replace Abstract: Rare disease diagnosis depends on expert reasoning that is scarce and difficult to transfer; off-the-shelf large language models (LLMs) rank the correct disease first in only 35.
By Minh-Ha Nguyen, Erica Gray, Bryce A. Schuler, Kevin W. Byram, Chih-Ting Yang, Fan Ma, Hua Xu, Wu-Chen Su, Chao Yan, Wei-Qi Wei, Adam Wright, Lisa Bastarache, Josh Peterson, Lingyao Li, Siyuan Ma, Undiagnosed Diseases Network, Rizwan Hamid, Thomas A. Cassini, Cathy Shyr
arXiv:2608. 11207v1 Announce Type: new Abstract: When two LLM agents with structurally opposed objectives interact across multiple turns, the absence of a shared goal function produces not competition but collapse: the visitor capitulates, the site agent stops varying its approach, and the conversation terminates without achieving either agent's stated objective.
By Alexander Liss, Nicholas Desmond, Santiago Gil Gallego
arXiv:2608. 11735v1 Announce Type: cross Abstract: Large language models (LLMs) often shift their outputs in response to implicit demographic cues even when users never state a demographic identity.
By Yueru Yan, Siqi Wu, Thai Le
arXiv:2608. 11582v1 Announce Type: cross Abstract: Identifying dengue virus-infected mosquitoes from control mosquitoes is a major challenge in analyzing mosquito locomotion behavior due to the small size and complexity of the video background.
By Danial Sharifrazi, Saadat Behzadi, Nouman Javed, Roohallah Alizadehsani, Prasad N. Paradkar, Asim Bhatti
arXiv:2608. 11249v1 Announce Type: cross Abstract: We study the problem of lossless text compression, motivated by the rapid growth in the collection and storage of digital textual data - including plain text, source code, and structured formats such as XML - and by recent advances in neural language model-based compression.
By Angelo Nardone, Paolo Ferragina
arXiv:2608. 11295v1 Announce Type: cross Abstract: Open-weight LLM agents are vulnerable to backdoors installed during fine-tuning, which may be undetectable if the trigger conditions are never met during testing.
By Gabriel Huang, Abhay Puri, L\'eo Boisvert, Alexandre Drouin, Perouz Taslakian, Spandana Gella, Christopher Pal
arXiv:2604. 17244v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents for sequential decision-making struggle to produce diverse outputs.
By Priya Gurjar, Md Farhan Ishmam, Kenneth Marino
arXiv:2608. 11552v1 Announce Type: cross Abstract: Uncertainty quantification (UQ) methods for language models are typically evaluated on single-turn outputs, where uncertainty is attached to one generated answer.
By Dylan Bouchard, Mohit Singh Chauhan
arXiv:2608. 11231v1 Announce Type: new Abstract: LLM serving is increasingly accelerated by position-independent caching (PIC).
By Yirui Liu, Ruoling Qi, Longwen Wang, Xuaner Wu, Jian Chen, Yuxin Jin, Jiawei Shao, Xuelong Li
arXiv:2608. 11584v1 Announce Type: new Abstract: Enterprise RAG deployments face a critical reliability gap: while LLMs satisfy 80% of individual constraints, only 26.
By Huiqi Miao, Xinbao Sun, Bo Wang, Fanyu Meng, Lijun Mei, Na Wu, Di Jin, Chao Deng, Junlan Feng
arXiv:2608. 12133v1 Announce Type: new Abstract: Enterprise guideline documents are heterogeneous and multimodal, combining narrative text, complex tables, and embedded images.
By Shivali Dalmia, Sumukha Thoppanahalli, Mohammadreza Sediqin, Abhishek Mukherji
arXiv:2608. 12304v1 Announce Type: new Abstract: Dynamic Master Logic (DML) provides a hierarchical framework for representing system behavior by linking functional objectives to underlying structural elements.
By Saman Marandi, Yu-Shu Hu, Mohammad Modarres
arXiv:2608. 11694v1 Announce Type: cross Abstract: A benchmark score comes from a single phrasing of each problem.
By Shailja Thakur, Sungeun An, Chad DeLuca, Hima Patel
arXiv:2608. 11256v1 Announce Type: new Abstract: Institutions use commercial AI detectors for academic integrity, yet detectors cannot distinguish AI editing from full LLM drafts and may treat both as misconduct.
By Jonathan A. Karr Jr, Grigorii Khvatskii, Ting Hua, Nitesh V. Chawla
arXiv:2607. 14616v3 Announce Type: replace Abstract: Vision-language models (VLMs) can describe a scene, but can they act well within one?
By Jasin Cekinmez, Addison J. Wu, Haotian Xia, Kyumin Andrew Shim, Anay Putty, Jinglin Xiao, Zhuohan Liu, Leo Liu, Weining Shen
arXiv:2608. 11623v1 Announce Type: cross Abstract: Recent advances in Large Language Models (LLMs) have spurred cross-modal solutions for time-series forecasting.
By Rentao Gu, Yihang Ding, Junjie Li, Yi Ding, Weijing Sang, Xiaoli Huo, Xin Qin, Yuefeng Ji
arXiv:2608. 11210v1 Announce Type: new Abstract: Bayesian calibration of process-based models requires a prior distribution for each model parameter.
By Patrik P. S\"uli, Gy\"orgy Eigner, Roland Holl\'os