Large language models

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

16,388 stories · RSS feed

arXiv AI

Aug 6

Strategic Evaluation of Planning Strategies for LLM Agents in Cyber-Physical Systems

arXiv:2608. 04265v1 Announce Type: cross Abstract: Evaluations of LLM planning agents largely ask whether a task succeeds or a declared plan is followed.

By J. de Curt\`o, I. de Zarz\`a

llms agents benchmarks

arXiv AI

Aug 6

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)

arXiv:2608. 04317v1 Announce Type: cross Abstract: Autonomous cyber defense systems based on Deep Reinforcement Learning (DRL) have attracted significant research attention, yet remain evaluated almost exclusively against static, heuristic red agents, leaving their robustness against adaptive threats critically understudied.

By Ryozo Masukawa, Ian Bryant, Armita Kazeminajafabadi, Sanggeon Yun, Hyunwoo Oh, SungHeon Jeong, Nathaniel D. Bastian, Mahdi Imani, Mohsen Imani

llms agents reinforcement-learning benchmarks

arXiv AI

Aug 6

HyPASE: Hyperbolic Geometry for Parameter-Efficient Speech Emotion Fine-Tuning Framework for Large Audio-Language Models

arXiv:2608. 04351v1 Announce Type: cross Abstract: Large Audio-Language Models (LALMs) excel at general speech understanding; however, adapting them to fine-grained tasks like Speech Emotion Recognition (SER) remains a significant bottleneck.

By Tian Jin, Ruikang Zhang, Zefeng Zhao, Ding Luo, Jin Zeng

llms fine-tuning multimodal benchmarks

arXiv AI

Aug 6

Training-Free Hashing-Based Attention via Binary Principal Components

arXiv:2608. 04405v1 Announce Type: cross Abstract: Long-context large language models (LLMs) are increasingly deployed in real-world applications, yet self-attention remains a major efficiency bottleneck -- especially during decoding -- due to the necessity of repeatedly processing ever-growing key-value (KV) caches.

By Daohai Yu, Zhanpeng Zeng, Keyu Chen, Wenhao Li, Zhifeng Shen, Luxi Lin, Ruizhi Qiao, Xing Sun, Rongrong Ji

llms efficiency benchmarks

arXiv AI

Aug 6

GeoReward: Mitigating Contextual Variable Overestimation in Vision-Language Models for Cross-Market Preference Prediction

arXiv:2608. 04504v1 Announce Type: cross Abstract: Vision-language models excel in many multimodal tasks but remain prone to a subtle yet impactful failure mode: they tend to overestimate dominant visual-textual cues while underestimating sparse but decision-critical contextual variables.

By Shuo Liu, Huixiang Cai, Weiru Zhang, Xiaoyi Zeng

llms diffusion reinforcement-learning fine-tuning multimodal safety

arXiv AI

Aug 6

CARVE: Cross-Slice Anisotropic Reallocation of Visual Evidence for Efficient 3D Medical Volume Understanding

arXiv:2608. 04515v1 Announce Type: cross Abstract: Slice-based MLLMs leverage mature 2D encoders by representing 3D volumes as sequences of 2D slices.

By Zhenyu Yi, Qiang Hu, Zhenhao Li, Jiaxuan Zhao, Yusong Sun, Lichi Zhang

llms benchmarks

arXiv AI

Aug 6

EASy: Towards Efficient LLM-Based Agentic System

arXiv:2608. 04588v1 Announce Type: cross Abstract: Agentic systems have emerged as a promising paradigm for solving complex tasks by coordinating specialized LLM-based agents.

By Junnan Liu, Linhao Luo, Thuy-Trang Vu, Gholamreza Haffari

llms agents reinforcement-learning robotics benchmarks

arXiv AI

Aug 6

Easy to Complete, Hard to Choose: Investigating LLM Performance on the ProverbIT Benchmark

arXiv:2608. 04670v1 Announce Type: cross Abstract: Large Language Models (LLMs) have transformed computational linguistics and achieved remarkable performance across numerous natural language processing tasks, yet significant gaps persist in understanding how these systems process culturally embedded linguistic expressions.

By Enrico Mensa, Lorenzo Zane, Calogero Jerik Scozzaro, Matteo Delsanto, Tommaso Milani, Daniele Paolo Radicioni

llms nlp benchmarks safety

arXiv AI

Aug 6

Teaching MLLMs to Say No: Generalized Referring Expression Comprehension via Refusal Calibrated GRPO

arXiv:2608. 04698v1 Announce Type: cross Abstract: We tackle the challenging yet underexplored task of Generalized Referring Expression Comprehension (GREC), which requires a model to localize the object described by a textual expression when it exists (positive sample) and to refuse output when it does not (negative sample).

By Xuzheng Yang, Jun Ling, Tao Huang, Caiyan Qin, Peng Wang

llms reinforcement-learning fine-tuning multimodal benchmarks safety

arXiv AI

Aug 6

Revisiting Generalization Across Difficulty Levels: It's Not So Easy

arXiv:2511. 21692v3 Announce Type: replace-cross Abstract: We investigate how well large language models (LLMs) generalize across different task difficulties, a key question for effective data curation and evaluation.

By Yeganeh Kordi, Nihal V. Nayak, Max Zuo, Ilana Nguyen, Stephen H. Bach

llms

arXiv AI

Aug 6

Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation

arXiv:2608. 04788v1 Announce Type: cross Abstract: Large language model agents are commonly trained through reinforcement learning with sparse trajectory-level rewards, which offer limited guidance on how strongly individual tokens should be updated.

By Yi Yang, Cong Qin, Xiaodan Liu, Chishui Chen, Qing Dong, Yan Zhang, Cao Liu, Zhao Yang, Lu Pan, Jiaye Lin, Yi Feng

llms agents reinforcement-learning efficiency

arXiv AI

Aug 6

A-SR: Self-Evolving Agentic LLMs for Symbolic Regression via Hierarchical Coordination

arXiv:2608. 04872v1 Announce Type: cross Abstract: Symbolic regression aims to discover closed-form equations from data, but existing LLM-guided methods often rely on a unified proposal loop that compresses heterogeneous search failures into a scalar score and a single prompt.

By Wenxiao Zhao, Dong Liu, Kaiyi Xu, Feng Liu, Zhen Zhao, Fei Ben, Shu Wang, Wenhao Li, Yingnian Wu, Fenghua Ling, Haobo Li, Lei Bai

llms agents fine-tuning

arXiv AI

Aug 6

SciCode-Verified: How Benchmark Defects Underestimated the Scientific-Coding Ability of Language Models

arXiv:2608. 04975v1 Announce Type: cross Abstract: SciCode is the standard measure of the scientific-coding ability of language models: research-level problems that demand both frontier scientific theory and its implementation as working numerical code.

By Sihan Hu, Lyuhan Huang, Youjin Deng, Kun Chen

llms benchmarks

arXiv AI

Aug 6

ArtAnno: Annotating Implicit Semantics in Artworks through LLM Agent-Driven Bidirectional Human-AI Augmentation

arXiv:2608. 05026v1 Announce Type: cross Abstract: High-quality annotation of artworks is essential for computational art research, yet extracting implicit semantics remains challenging due to the reliance on culturally grounded meanings and deep contextual knowledge behind the images.

By Xiaoyan Gu, Yifang Wang, Wenqing Zheng, Haozhong Liu, Yixia Zheng, Peiyi Jiang, Wenjie Ning, Wei Zhang, Wei Chen

llms rag agents

arXiv AI

Aug 6

Hardware Design and Security in the Era of Chiplets and LLMs

arXiv:2608. 05063v1 Announce Type: cross Abstract: The semiconductor industry is undergoing a dual revolution: the shift toward heterogeneous 2.

By Johann Knechtel, Ozgur Sinanoglu, Paul V. Gratz, Ramesh Karri

llms benchmarks

arXiv AI

Aug 6

Text2GraphQuery-Bench: A Text to Graph Query Benchmark

arXiv:2602. 11745v2 Announce Type: replace Abstract: Graph models are fundamental to data analysis in domains rich with complex relationships.

By Songlin Lyu, Lujie Ban, Zihang Wu, Tianqi Luo, Jirong Liu, Ayoub Moussaid, Oskar van Rest, Heng Lin, Chenhao Ma, Nan Tang, Shipeng Qi, Yongchao Liu, Zhan Qiu, Juelu Zhang, Jiajun Zheng

llms fine-tuning benchmarks data-engineering

arXiv AI

Aug 6

Risk Is Not the Target: A Monotonic Framework for Evaluating Wildfire Operational Risk Signals

arXiv:2607. 21597v2 Announce Type: replace Abstract: Evaluating wildfire risk systems using standard machine-learning metrics such as F1-score or IoU is fundamentally flawed: these metrics assess event prediction accuracy, not the operational coherence of a continuous risk signal.

By Nicolas Caron, Christophe Guyeux, Hassan Noura, Maxime Coulmeau, Benjamin Aynes

llms agents

arXiv AI

Aug 6

Pun Intended: Multi-Agent Translation of Wordplay with Contrastive Learning and Phonetic-Semantic Embeddings for CLEF JOKER 2025 Task 2

arXiv:2507. 06506v2 Announce Type: replace-cross Abstract: Translating wordplay across languages presents unique challenges that have long confounded both professional human translators and machine translation systems.

By Russell Taylor, Benjamin Herbert, Michael Sana

llms rag agents nlp benchmarks

arXiv AI

Aug 6

Arnold: A multi-task, multi-embodiment muscle transformer policy

arXiv:2508. 18066v2 Announce Type: replace-cross Abstract: Controlling high-dimensional and nonlinear musculoskeletal models of the human body is a foundational scientific challenge.

By Boshi An, Alberto Silvio Chiappa, Merkourios Simos, Chengkun Li, Alexander Mathis

llms agents reinforcement-learning robotics

arXiv AI

Aug 6

RooflineBench: A Benchmarking Framework for On-Device LLMs via Roofline Analysis

arXiv:2602. 11506v4 Announce Type: replace-cross Abstract: The transition toward localized intelligence through Small Language Models (SLMs) has intensified the need for rigorous performance characterization on resource-constrained edge hardware.

By Zhen Bi, Xueshu Chen, Luoyang Sun, Yuhang Yao, Qing Shen, Jungang Lou, Cheng Deng

llms benchmarks

Get the daily briefing