Large language models

Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.

14,004 stories · RSS feed

arXiv AI

2d ago

Synchronized Logit Steering: Real-world Steganography

arXiv:2608. 14697v1 Announce Type: new Abstract: Steganography in large language models offers a way to embed hidden messages within natural-sounding text.

By Andrew Rufail, Aadi Dash, Onir Narahari, Ethan Mui, Mahi Gajare, Prakhar Tiwari, Shrija Makapothula, Nick Cui

llms rag

arXiv AI

2d ago

CEDAR-GRPO: Process-Aware Reinforcement Learning for General Abductive Reasoning in LLMs

arXiv:2608. 14791v1 Announce Type: new Abstract: Abductive reasoning, often characterized as inference to the best explanation, is central to explanation under uncertainty, from everyday sense-making and investigation to scientific discovery.

By Moein Salimi, Danial Parnian, Shaygan Adim, Amirmohammad Ebrahiminasab, Nima Alighardashi, Parsa Gholami, Sahand Akramipour, Mahdi Jafari Siavoshani, Mohammad Hossein Rohban

llms reinforcement-learning benchmarks

arXiv AI

2d ago

Accuracy and Reliability of Large Language Models in Cosmetic Chemistry and Skin Health: A Benchmarking Study

arXiv:2608. 14631v1 Announce Type: new Abstract: As consumers increasingly turn to AI chatbots for skincare advice, the technical accuracy of Large Language Models (LLMs) in cosmetic chemistry remains largely under-evaluated.

By Amelia Liu

llms fine-tuning benchmarks

arXiv AI

2d ago

Evaluating Multimodal LLMs across Text and Audio Modalities for Accessible Disaster Assistance

arXiv:2608. 14651v1 Announce Type: new Abstract: Effective disaster risk communication is a foundational humanitarian challenge, yet current emergency infrastructure fails to meet the needs of individuals with access and functional needs, including hard-of-hearing individuals, pregnant women, mothers with toddlers, and elderly individuals with dementia.

By Anuridhi Gupta, Samara Mansoor, Hemant Purohit

llms multimodal benchmarks

arXiv AI

2d ago

Beyond Correctness: Toward Automated Novelty Verification with Lean 4

arXiv:2608. 14669v1 Announce Type: new Abstract: Artificial intelligence systems applied to mathematics verify correctness but not novelty: an automatically generated theorem can compile in Lean without errors and yet be an already known result.

By Ayrton Porto

llms benchmarks

arXiv AI

2d ago

Generated Context versus Governed State: Functional Conditions for Accountable Longitudinal Clinical Reasoning

arXiv:2608. 14804v1 Announce Type: new Abstract: Large language models (LLMs) have become the dominant interface of clinical artificial intelligence, yet the interface they expose (text in, text out, one context window at a time) maintains no explicit, persistent, governed representation of what is currently true about a patient.

By Augusto Bernardo Pissarra, Victor Lorena de Farias Souza

llms

arXiv AI

2d ago

LLMs Can Predict Failure Risk, But Struggle to Predict Which Collaboration Protocol Pays Off: Cost-Aware Protocol Routing Across Reasoning Tasks

arXiv:2608. 14927v1 Announce Type: new Abstract: Multi-agent large language model (LLM) systems can improve reasoning by spending more computation, but deployment requires deciding when extra collaboration is worth its cost.

By Chih-Hsuan Yang, Jingyan Jiang, Cheng-Hau Yang, Vikram Vasudevan, Huihuo Zheng, Venkatram Vishwanath, Rajeev Thakur

llms agents benchmarks

arXiv AI

2d ago

Large Language Models and their Awareness of Mechanics and Spatial Geometry

arXiv:2608. 14615v1 Announce Type: new Abstract: Large Language Models (LLMs) perform well on established code-generation and mathematical-reasoning benchmarks, but their capabilities in mechanics and spatial geometry, here denoted as mechanical engineering awareness, has not been quantified systematically.

By Johannes Gerstmayr, Sebastian Weyrer, Tobias M\"oltner, Peter Manzl, Michael Pieber

llms benchmarks

arXiv AI

2d ago

Do LLM Agents Negotiate Rationally? A Mechanism-Design Framework for Verifiable Multi-Agent Interaction over A2A/MCP

arXiv:2608. 14613v1 Announce Type: new Abstract: Modern LLM-agent frameworks increasingly interoperate through standards such as Anthropic's Model Context Protocol (MCP) for agent-to-tool access and Google's Agent2Agent (A2A) protocol for agent delegation and negotiation.

By Wael Albayaydh, Rui Zhao

llms agents benchmarks

arXiv AI

2d ago

Learning Agent Execution for KV-Cache Management in Agentic Serving

arXiv:2608. 14624v1 Announce Type: new Abstract: Multi-agent LLM systems have emerged as an important deployment paradigm for AI services, where each user request is decomposed into a sequence of specialized agents.

By Rui Zhang, Chaeeun Kim, Shaoting Feng, Kuntai Du, Yuhan Liu, Yi Zhong, Cheng-Wei Ching, Junchen Jiang, Liting Hu

llms agents efficiency

arXiv AI

2d ago

What the Reranker Sees: Multi-Aspect Page Annotation for Long-Document Multimodal Question Answering

arXiv:2608. 14841v1 Announce Type: new Abstract: Long-document visual question answering (VQA) over documents of tens to hundreds of pages mixing text, tables, charts, and figures typically follows retrieve-then-read pipelines.

By Guanchen Wu, Jiayuan Ding, Subhabrata Mukherjee, Carl Yang

llms nlp multimodal

arXiv AI

2d ago

Reconstruction: A Blind Benchmark for Recovering Research Ideas from Pre-Publication Bibliographies

arXiv:2608. 16645v1 Announce Type: new Abstract: Can a language model recover the true research idea of a published paper when given only that paper's pre-publication bibliography?

By Shaolong Chen, Yanlin Fei, Nazhou Liu, Xinmiao Yu, Lei Li, Rahul Thapa, Madalina Ciobanu, Qingqing Mao, Ritankar Das

llms agents benchmarks

arXiv AI

2d ago

OGX: An Open-Source, Vendor-Neutral Generative AI Application Server

arXiv:2608. 14580v1 Announce Type: new Abstract: OGX (Open GenAI Stack) is an open-source AI application server and Python library that implements the APIs of major frontier labs (OpenAI, Anthropic, Google) with pluggable backend providers.

By Francisco Javier Arceo, S\'ebastien Han, Matthew Farrellee, Charlie Doern, Yuan Tang, Derek Higgins, Varsha Prasad Narsing, Gordon Sim, Sumanth Kamenani, Ben Browning, Raghotham Murthy

llms rag agents safety

arXiv AI

2d ago

Euclid-Omni : A Unified Neuro-Symbolic Framework for Plane Geometry

arXiv:2608. 14585v1 Announce Type: new Abstract: Euclidean geometry is a compelling testbed for AI reasoning, as it demands the combination of intuitive diagram understanding, axiomatic deduction, and algebraic computation.

By Zhaoyu Li, Hangrui Bi, Youyuan Zhang, Wenjie Ma, Zenan Li, Zhaolei Zhang, Xujie Si, Kaiyu Yang

llms multimodal benchmarks

arXiv AI

2d ago

Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement

arXiv:2608. 14590v1 Announce Type: new Abstract: LLM agents increasingly perform irreversible real-world actions, including database updates, API calls, file operations, and autonomous use of tools.

By Pierre Dantas, Lucas Cordeiro, Ehsan Nowroozi, Tihanyi Norbert

llms agents safety

arXiv AI

2d ago

The Unwritten Benchmark: A New Challenge for Multimodal Machine Learning in Abstract Perceptual Reasoning

arXiv:2608. 14558v1 Announce Type: new Abstract: Current multimodal models have demonstrated remarkable proficiency in recognizing static visual and auditory content.

By Garima Arya Yadav, Nilay Yilmaz, Yezhou Yang

llms multimodal benchmarks

arXiv AI

2d ago

ATLAS: Scaffold-Free Algorithm Synthesis by LLMs via Embedding-Guided Quality-Diversity Search

arXiv:2608. 15546v1 Announce Type: new Abstract: Most LLM-based automated algorithm design methods optimize a designated component within a human-specified scaffold, fixing overall organization and component interactions.

By Danial Yazdani, Mohammad Nabi Omidvar, Yuan Sun, Maksud Ibrahimov, Xiaodong Li

llms rag benchmarks

arXiv AI

2d ago

Position: Evaluations of AI Moral Reasoning Still Miss Half of the Picture

arXiv:2608. 14566v1 Announce Type: new Abstract: Recent work on evaluating the moral competence of large language models (LLMs) has focused primarily on what we call the moral value problem, i.

By Aidan Kierans, Ritam Dutt, Kaley Rittichier, Shiri Dori-Hacohen, Avijit Ghosh

llms benchmarks

arXiv AI

2d ago

When Do LLMs Apply the Wrong Law? Diagnosing LLM Failures in Temporal Legal Reasoning

arXiv:2608. 14610v1 Announce Type: new Abstract: Legal reasoning tasks such as legal judgment prediction (LJP) require identifying the temporally correct version of the law governing a case -- a capability we term temporal applicable-law determination.

By Yiqian Huang, Shuyuan Zheng, Qianying Liu, Shaowen Peng, Yuntao Kong, Kotaro Funakoshi, Chuan Xiao, Manabu Okumura, Yang Cao

llms benchmarks safety

arXiv AI

2d ago

What Do Compliance Detectors Read? An Audit of Activation Probes and Guard Models

arXiv:2608. 16852v1 Announce Type: new Abstract: Regulatory compliance monitoring in deployed language models is increasingly implemented as a legal and audit control, checking model outputs against written rules spanning data protection, healthcare, financial regulation, and platform policy.

By Saisab Sadhu, Aadit Sengupta, Vinay Kumar Sankarapu, Pratinav Seth

llms benchmarks