Large language models

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

31,091 stories · RSS feed

arXiv AI

Jun 4

Failed Reasoning Traces Tell You What Is Fixable (But Not by Reading Them)

arXiv:2606. 05145v1 Announce Type: cross Abstract: When post-trained language models fail on reasoning problems, the common test-time-scaling response is to spend more compute on additional attempts, and the failed traces play no further role.

By Nizar Islah, Istabrak Abbes, Irina Rish, Sarath Chandar, Eilif B. Muller

llms

arXiv AI

Jun 4

Invariant Gradient Alignment for Robust Reasoning Distillation

arXiv:2606. 05025v1 Announce Type: cross Abstract: Large language models (LLMs) suffer from shortcut learning: they systematically fail on out-of-distribution (OOD) inputs whose semantic surface differs from training data, even when the logical structure is identical.

By Zehua Cheng, Wei Dai, Jiahao Sun

llms fine-tuning efficiency benchmarks safety

arXiv AI

Jun 4

Self-Reflective APIs: Structure Beats Verbosity for AI Agent Recovery

arXiv:2606. 05037v1 Announce Type: cross Abstract: When an AI agent calls an API and hits a validation error, it needs more than what went wrong -- it needs what to do next.

By Arquimedes Canedo, Grama Chethan

llms agents benchmarks safety

arXiv AI

Jun 4

Learning While Acting: A Skill-Enhanced Test-Time Co-Evolution Framework for Online Lifelong Learning Agents

arXiv:2606. 04815v1 Announce Type: cross Abstract: Lifelong learning is essential for Large Language Model (LLM) agents operating in dynamic, interactive environments.

By Bo Mao, Jie Zhou, Yutao Yang, Xin Li, Xian Wei, Qin Chen, Xingjiao Wu, Liang He

llms agents reinforcement-learning

arXiv AI

Jun 4

Unpredictable Safety: Domain-Dependent Compliance and the Transparency Gap in Open-Weight LLMs

arXiv:2606. 04035v1 Announce Type: cross Abstract: We present a systematic study of domain-dependent safety behavior in open-weight LLMs: 7 standardized experiments across 7 ethical domains, testing 5 models (12B--70B) in 4,200 interactions with dual-judge validation.

By Zacharie Bugaud

llms safety

arXiv AI

Jun 4

Implement Kubernetes Pod-Level Remote Attestation for Confidential Workloads on dstack

arXiv:2606. 03323v2 Announce Type: replace-cross Abstract: The rise of LLM-as-a-Service and other confidential cloud workloads demands cryptographic proof that user data is processed in a trusted, untampered environment.

By Yang Yang, Kevin Wang, Yuanhai Luo, Hang Yin, Jie Cai, Shunfan Zhou, Wenfeng Wang

llms

arXiv AI

Jun 4

Inference-Time Vulnerability Beyond Shallow Safety: Alignment Along Generation Trajectories

arXiv:2606. 04778v1 Announce Type: new Abstract: Safety-aligned Large Language Models (LLMs) remain vulnerable to interventions during inference that redirect generation toward harmful outputs.

By Kyungmin Park, Taesup Kim

llms safety

arXiv AI

Jun 4

Structured Prompt Optimization Meets Reinforcement Learning for Global and Local Interpretability over Complex Text

arXiv:2605. 29076v2 Announce Type: replace-cross Abstract: LLMs have advanced text classification, yet existing paradigms face a trade-off: supervised (label only) fine-tuning is scalable but offers limited reasoning on complex text and lacks broader model transparency, while discrete prompt optimization offers human-readable instructions but struggles with performance and scalability.

By Tianyang Zhou, Wenbo Chen, Pierre Jinghong Liang, Leman Akoglu

llms nlp reinforcement-learning fine-tuning efficiency benchmarks safety

arXiv AI

Jun 4

Aryabhata 2: Scaling Reinforcement Learning for Advanced STEM Reasoning

arXiv:2605. 28829v2 Announce Type: replace-cross Abstract: Competitive STEM examinations such as JEE and NEET require multi-step symbolic reasoning, precise numerical computation, and deep conceptual understanding across physics, chemistry, and mathematics.

By Ritvik Rastogi, Vishal Singh, Tejas Chaudhari, Sandeep Varma

llms reinforcement-learning benchmarks

arXiv AI

Jun 4

Luminol-AIDetect: Fast Zero-shot Machine-Generated Text Detection based on Perplexity under Text Shuffling

arXiv:2604. 25860v2 Announce Type: replace-cross Abstract: Machine-generated text (MGT) detection requires identifying structurally invariant signals across generation models, rather than relying on model-specific fingerprints.

By Lucio La Cava, Andrea Tagarelli

llms benchmarks safety

arXiv Machine Learning

Jun 4

Efficient Reasoning on the Edge

arXiv:2603. 16867v2 Announce Type: replace Abstract: Large language models (LLMs) with chain-of-thought reasoning achieve state-of-the-art performance across complex problem-solving tasks, but their verbose reasoning traces and large context requirements make them impractical for edge deployment.

By Yelysei Bondarenko, Thomas Hehn, Rob Hesselink, Romain Lepert, Fabio Valerio Massoli, Evgeny Mironov, Leyla Mirvakhabova, Tribhuvanesh Orekondy, Spyridon Stasis, Andrey Kuzmin, Anna Kuzina, Markus Nagel, Ankita Nayak, Corrado Rainone, Ork de Rooij, Paul N Whatmough, Arash Behboodi, Babak Ehteshami Bejnordi

llms reinforcement-learning fine-tuning efficiency benchmarks

arXiv AI

Jun 4

Scaling Self-Evolving Agents via Parametric Memory

arXiv:2606. 04536v1 Announce Type: new Abstract: Existing memory-augmented LLM agents store past experience exclusively in prompt space, as textual summaries or retrieved passages, while keeping model parameters frozen throughout a rollout.

By Tao Ren, Weiyao Luo, Hui Yang, Rongzhi Zhu, Xiang Huang, Yuchuan Wu, Bingxue Chou, Jieping Ye, Jiafeng Liang, Yongbin Li, Yijie Peng

llms agents reinforcement-learning fine-tuning

arXiv Machine Learning

Jun 4

Sequential Data Poisoning in LLM Post-Training

arXiv:2606. 04929v1 Announce Type: new Abstract: LLM post-training proceeds through multiple stages, e.

By Jack Sanderson, Yihan Wang, Xiaoqian Lu, Gautam Kamath, Yiwei Lu

llms reinforcement-learning fine-tuning

arXiv Machine Learning

Jun 4

TANDEM: Bi-Level Data Mixture Optimization with Twin Networks

arXiv:2606. 04401v1 Announce Type: new Abstract: The capabilities of large language models (LLMs) significantly depend on training data drawn from various domains.

By Jiaxing Wang, Deping Xiang, Jin Xu, Mingyang Yi, Guoqiang Gong, Zicheng Zhang, Haoran Li, Pengzhang Liu, Zhen Chen, Ke Zhang, Ju Fan, Qixiang Jiang

llms fine-tuning

arXiv AI

Jun 4

Dynamic Content Moderation in Livestreams: Combining Supervised Classification with MLLM-Boosted Similarity Matching

arXiv:2512. 03553v3 Announce Type: replace-cross Abstract: Content moderation remains a critical yet challenging task for large-scale user-generated video platforms, especially in livestreaming environments where moderation must be timely, multimodal, and robust to evolving forms of unwanted content.

By Wei Chee Yew, Hailun Xu, Sanjay Saha, Xiaotian Fan, Hiok Hian Ong, David Yuchen Wang, Kanchan Sarkar, Zhenheng Yang, Danhui Guan

llms multimodal safety

arXiv AI

Jun 4

Geometry-Aware Hallucination Detection in Large Language Models

arXiv:2601. 06196v3 Announce Type: replace-cross Abstract: Large language models (LLMs) frequently generate factually incorrect or unsupported content, commonly referred to as hallucinations.

By Bodla Krishna Vamshi, Rohan Bhatnagar, Haizhao Yang

llms rag nlp fine-tuning benchmarks safety

arXiv AI

Jun 4

Transformer-Based Autonomous Driving Models and Deployment-Oriented Compression: A Survey

arXiv:2304. 10891v3 Announce Type: replace-cross Abstract: Transformer-based models are becoming a central paradigm in autonomous driving because they can capture long-range spatial dependencies, multi-agent interactions, and multimodal context across perception, prediction, and planning.

By Juan Zhong, Yuhang Shi, Zukang Xu, Xi Chen

llms agents robotics efficiency multimodal safety

arXiv AI

Jun 4

From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents

arXiv:2606. 04329v1 Announce Type: cross Abstract: Memory is a core component of AI agents, enabling them to accumulate knowledge across interactions and improve performance.

By Pritam Dash, Tongyu Ge, Aditi Jain, Tanmay Shah, Zhiwei Shang

llms agents benchmarks safety

arXiv AI

Jun 4

Recover-LoRA for Aggressive Quantization: Reclaiming Accuracy in 2-Bit Language Models via Low-Rank Adaptation with Knowledge Distillation on Synthetic Data

arXiv:2606. 04238v1 Announce Type: cross Abstract: Aggressive weight quantization to 2-bit precision offers substantial throughput and memory gains for large language model (LLM) inference, but typically incurs severe accuracy degradation.

By Devleena Das, Rajeev Patwari, Elliott Delaye, Ashish Sirasao

llms fine-tuning efficiency benchmarks

arXiv AI

Jun 4

BiasGRPO: Stabilizing Bias Mitigation in High-Variance Reward Landscapes via Group-Relative Policy Optimization

arXiv:2606. 04807v1 Announce Type: new Abstract: Mitigating social bias in Large Language Models (LLMs) presents a distinct alignment challenge: unlike verifiable tasks, bias lacks a single ground truth, creating a high-variance, subjective reward landscape.

By Saket Reddy, Ke Yang, ChengXiang Zhai

llms reinforcement-learning fine-tuning benchmarks safety

Get the daily briefing