Large language models

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

20,725 stories · RSS feed

arXiv AI

Jul 22

Relay-Bench: Evaluating LLMs on Multi-Domain Reasoning Chains

arXiv:2607. 18438v1 Announce Type: cross Abstract: Introducing Relay-Bench, an unsaturated, holistic, text-only benchmark that measures LLMs' ability to complete an assortment of tasks from distinct domains in a single prompt.

By Liam Swayne

llms multimodal benchmarks

arXiv AI

Jul 22

MUX: Continuous Reasoning via Multiplexed Tokens

arXiv:2607. 18264v1 Announce Type: new Abstract: Language models solve complex problems by articulating intermediate reasoning steps in natural language.

By Ayhan Suleymanzade, Halil Alperen Gozeten, Michael Bronstein, \.Ismail \.Ilkan Ceylan, Jinwoo Kim

llms diffusion efficiency benchmarks

arXiv AI

Jul 22

Learning to Make Friends: Coaching LLM Agents toward Emergent Social Ties

arXiv:2510. 19299v2 Announce Type: replace Abstract: Can large language model (LLM) agents reproduce the complex social dynamics that characterize human online behavior -- shaped by homophily, reciprocity, and social validation -- and what memory and learning mechanisms enable such dynamics to emerge?

By Philipp J. Schneider, Lin Tian, Marian-Andrei Rizoiu

llms agents

arXiv AI

Jul 22

ISO: An RLVR-Native Optimization Stack

arXiv:2607. 19331v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is rapidly advancing the reasoning capabilities of language models, yet the optimization layer that converts reward feedback into weight-space updates remains poorly understood.

By Hanqing Zhu, Wenyan Cong, Zhizhou Sha, Sagnik Mukherjee, Xinyuan Song, David Gonz\'alez-Mart\'inez, Xiaoxia Wu, Yuandong Tian, Shiwei Liu, David Z. Pan, Zhangyang "Atlas" Wang

llms reinforcement-learning efficiency

arXiv AI

Jul 22

The Story Shapes the Agent: Narrative Priors in LLM Behavior

arXiv:2607. 18566v1 Announce Type: cross Abstract: Persona prompting is widely used to steer LLM agent behavior, yet the narrative framing of a task can matter more than the assigned persona.

By Yixuan Wang, James Lester, Shashank Srivastava

llms agents

arXiv AI

Jul 22

When JSON Is Not Enough: Semantic Reliability of Schema-Constrained LLM Ordering Agents

arXiv:2607. 18261v1 Announce Type: new Abstract: LLM agents are increasingly used as transaction compilers: a user states an intent in natural language, and the model emits a structured object that an API can execute.

By Yin Li

llms agents benchmarks

arXiv AI

Jul 22

The Economics of Autonomy: Real-Time Risk Indexing for Insurable AI-Driven 6G Systems

arXiv:2607. 18267v1 Announce Type: cross Abstract: The transition to sixth-generation (6G) networks transforms wireless infrastructure into a cognitive substrate supporting Vehicle-to-Everything (V2X), Industrial IoT (IIoT), and Integrated Sensing and Communication (ISAC).

By Anthony Kiggundu, Michael Zentarra, Christoph Lipps, Hans D. Schotten

llms agents fine-tuning safety

arXiv AI

Jul 22

Inference-Time Steering for Cross-Lingual Factual Consistency in LLMs

arXiv:2607. 19243v1 Announce Type: cross Abstract: Although Large Language Models (LLMs) demonstrate remarkable multilingual fluency, their internal knowledge representations remain disproportionately biased toward high-resource languages.

By Alexander Manev

llms reinforcement-learning robotics benchmarks safety

arXiv AI

Jul 22

Operational Hallucination and Safety Drift in AI Agents

arXiv:2607. 18366v1 Announce Type: new Abstract: Large language models (LLMs) serving as planners in tool-using autonomous agents introduce dynamic reliability risks in multi-turn execution.

By Shasha Yu, Fiona Carroll, Barry L. Bentley

llms agents benchmarks safety

arXiv AI

Jul 22

Benchmarking Generalization in Financial Statement Fraud Detection: robust evaluation and novel tasks

arXiv:2607. 19259v1 Announce Type: cross Abstract: Financial statement fraud detection (FSFD) is crucial for market integrity but faces challenges from increasingly sophisticated schemes and under-utilized textual data in financial reports.

By Guy Stephane Waffo Dzuyo (Forvis Mazars, LORIA CNRS Universit\'e de Lorraine), Ga\"el Guibon (LORIA CNRS Universit\'e de Lorraine, LIPN CNRS Universit\'e Sorbonne Paris Nord), Christophe Cerisara (LORIA CNRS Universit\'e de Lorraine), Luis Belmar-Letelier (Forvis Mazars)

llms benchmarks

arXiv AI

Jul 22

Binding Drift in Multi-Step Tool-Augmented Agents

arXiv:2607. 18316v1 Announce Type: cross Abstract: Tool-augmented language-model agents execute multi-step workflows over external systems, resolving an entity once and then acting on it across subsequent steps.

By Rahul Suresh Babu, Shashank Indukuri

llms agents

arXiv Machine Learning

Jul 22

Breaking Feedback-Blindness: Utility-Augmented Transformer for Sequential Decision Making

arXiv:2607. 18910v1 Announce Type: new Abstract: Sequential decision making in non-stationary and partially observable environments requires rapid adaptation to latent regime changes.

By Yuyang Shen, Shan Dai, Daimin Chen

llms benchmarks

arXiv AI

Jul 22

State Compression in Two-Agent LLM Relays: A Closed-World Study of Constraint Preservation

arXiv:2607. 18265v1 Announce Type: new Abstract: Long-running Large Language Model (LLM)-based agents often accumulate large intermediate traces containing audits, eliminations, and numeric calculations.

By Anantha Sharma, Sheeba Elizabeth John, Kaarthik Senthil Kumar, Saratsuhas Vijayababu

llms rag agents nlp efficiency

arXiv AI

Jul 22

MechAInistic: An LLM-guided Multi-Agent System for Reasoning over Genome-Scale Constraint-Based Metabolic Models

arXiv:2607. 18249v1 Announce Type: cross Abstract: Constraint-based metabolic modeling is a powerful way to study the mechanistic basis of cellular states and disease, but its effective use demands substantial computational expertise and careful coordination of multi-step analyses.

By Josh Loecker, Narayna Puraja, William Bryan, Bhanwar Lal Puniya, Ahmed Abdeen Hamed, Tom\'a\v{s} Helikar

llms agents

arXiv AI

Jul 22

AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents

arXiv:2607. 18754v1 Announce Type: new Abstract: LLM agent failures are difficult to debug because the step where an error surfaces is often not the one that caused it.

By Kunlun Zhu, Xuyan Ye, Zhiguang Han, Yuchen Zhao, Bingxuan Li, Weijia Zhang, Muxin Tian, Xiangru Tang, Pan Lu, James Zou, Jiaxuan You, Heng Ji

llms agents benchmarks

arXiv AI

Jul 22

Reasoning Before Translation: Enhancing Legal Machine Translation with Structured Reasoning

arXiv:2607. 19181v1 Announce Type: cross Abstract: Neural machine translation (NMT) in the legal domain is a linguistically and conceptually demanding task, primarily due to the complexity of legal language and the high level of precision it requires.

By Aixiu An, Michael Jungo, Eloi Eynard, Mark Drenhaus, Andreas Fischer, Jean Hennebert, S\'ebastien Rumley

llms nlp reinforcement-learning fine-tuning benchmarks

arXiv AI

Jul 22

Fence: Specialized SLM Guardrails for LLM Applications

arXiv:2607. 18268v1 Announce Type: new Abstract: Real-world applications that use closed-source large language models (LLMs) need advanced safety measures that go beyond the basic content filters.

By Kumud Lakara, Ruibo Shi, Fran Silavong

llms diffusion safety

arXiv AI

Jul 22

LLM Detection as an Intervention: Downstream Impact under Strategic User Behavior

arXiv:2607. 19300v1 Announce Type: new Abstract: As LLM adoption becomes more widespread, there is a growing interest in detecting LLM-generated content, for example through LLM detection tools and through heuristics based on language patterns.

By Meena Jagadeesan, Tatsunori Hashimoto, Jon Kleinberg

llms

arXiv AI

Jul 22

The Price of Reasoning: Cost-Quality Tradeoffs in Reinforcement Learning for Neural Machine Translation

arXiv:2607. 19226v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has been established as a viable paradigm for the post-training of Large Language Models (LLMs), including downstream tasks, such as Neural Machine Translation (NMT).

By Michael Jungo, Aixiu An

llms nlp reinforcement-learning

arXiv AI

Jul 22

Sequential Learner Modeling Using Multi-Relational Graph Convolutional Networks

arXiv:2607. 19253v1 Announce Type: new Abstract: User modeling is a critical task in a variety of personalized systems.

By Rawaa Alatrash, Mohamed Amine Chatti, Hong Yang, Yumeng Wang

llms rag

Get the daily briefing