arXiv AI
Jul 14
AgentCheck: A Reproduce-Intervene-Mitigate Workbench for LLM Agents over MCP
arXiv:2607. 11098v1 Announce Type: cross Abstract: Tool-using LLM agents are mostly evaluated assuming all tools work.
Large language models
Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv AI
Jul 14
Large language model agents accelerate inverse design of metal-organic frameworks for gas separation
arXiv:2607. 10559v1 Announce Type: new Abstract: Metal-organic frameworks (MOFs) offer a highly modular platform for adsorptive gas separation, yet their vast reticular design space makes inverse design difficult under simultaneous constraints of chemical validity, separation performance, and structural diversity.
arXiv Machine Learning
Jul 14
Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data
arXiv:2607. 11883v1 Announce Type: new Abstract: Compression is fundamental to intelligence.
arXiv AI
Jul 14
How Do Practitioners Build SE Agents? Insights from a Mixed-Methods Study
arXiv:2607. 10856v1 Announce Type: cross Abstract: The rise of Software Engineering (SE) agents, i.
arXiv AI
Jul 14
InqEduAgent: Adaptive AI Learning Partners with Gaussian Process Augmentation
arXiv:2508. 03174v4 Announce Type: replace Abstract: Collaborative partnerships play a crucial role in inquiry-oriented education.
arXiv Machine Learning
Jul 14
Attribution-Guided Continual Learning for Large Language Models
arXiv:2605. 05285v2 Announce Type: replace Abstract: Large language models (LLMs) often suffer from catastrophic forgetting in continual learning: after learning new tasks sequentially, they perform worse on earlier tasks.
arXiv Machine Learning
Jul 14
Tokenizing Numerical and Embedding Features for LLM RecSys
arXiv:2607. 10016v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as backbone architectures for recommender systems because of their strong sequence modeling and representation learning capabilities.
arXiv AI
Jul 14
Exploring Agentic Workflows for Generating High Quality Math Visual Aids
arXiv:2607. 09839v1 Announce Type: new Abstract: Mathematical diagrams play a crucial role in K 12 education, both as problem components and as scaffolding for student comprehension.
arXiv AI
Jul 14
CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning
arXiv:2512. 02551v3 Announce Type: replace-cross Abstract: In this paper, we propose CUDA-L2, a system that combines large language models (LLMs) and reinforcement learning (RL) to automatically optimize Half-precision General Matrix Multiply (HGEMM) CUDA kernels.
arXiv AI
Jul 14
Adaptive Model Compression (AMC): Saliency-Driven Resource Allocation for Ultra-Low-Power Transformer Inference
arXiv:2607. 10109v1 Announce Type: cross Abstract: Deploying large-scale transformer models on resource-constrained edge devices remains a challenge due to the high energy and memory overhead inherent in static inference, which processes simple and complex tokens with uniform intensity.
arXiv AI
Jul 14
Structured Thoughts For Improved Reasoning And Context Pruning
arXiv:2607. 10386v1 Announce Type: cross Abstract: Large language models (LLMs) excel at generating long chains of thought, but long reasoning traces are often verbose and memory-inefficient.
arXiv AI
Jul 14
Enabling Agents to Communicate Entirely in Latent Space
arXiv:2511. 09149v5 Announce Type: replace-cross Abstract: While natural language is the de facto communication medium for LLM-based agents, it presents a fundamental constraint.
arXiv AI
Jul 14
Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals
arXiv:2607. 11505v1 Announce Type: cross Abstract: Post-training is essential for refining the domain-specific capabilities of large language models (LLMs), yet existing reward optimization and distribution matching methods tightly couple policy exploration with distribution alignment.
arXiv AI
Jul 14
Semantic Drift and the Stability of Operator Control in Reasoning-Class Decision Support Systems
arXiv:2607. 09790v1 Announce Type: new Abstract: The article investigates the fundamental problem of ensuring the stability of operator control and preserving goal-targeting in hybrid human-machine decision support systems (DSS) of a new generation.
arXiv AI
Jul 14
Confining Nondeterminism: AI-Driven Research Systems as DBMSs for Reliable, Non-Wasteful, Transparent, and Collaborative Research [Vision]
arXiv:2607. 10508v1 Announce Type: cross Abstract: LLM agents that conduct research (proposing ideas, writing and running code, analyzing results) can already carry a study from research question to figures, yet cannot be fully trusted.
arXiv AI
Jul 14
LSTrans: Efficient Knowledge Transfer for Lightweight and Automated ECG Classification
arXiv:2607. 10784v1 Announce Type: cross Abstract: Deploying deep learning models for automated electrocardiogram classification on resource-constrained wearable devices remains challenging due to high computational costs.
arXiv AI
Jul 14
Enhancing LLMs through human feedback: a journey towards self-improvement
arXiv:2607. 11267v1 Announce Type: cross Abstract: In the rapidly evolving landscape of information retrieval systems, the ability to adapt and improve through user feedback is paramount.
arXiv AI
Jul 14
The Nuts and Bolts of Natural Language to SQL Translation: A Systematic Analysis of Model Pipeline Optimisation Approaches and their Interactions
arXiv:2607. 10911v1 Announce Type: cross Abstract: In the age of large language models, Natural Language to SQL (NL2SQL) translation remains an open problem with many useful applications.
arXiv AI
Jul 14
Graph Optimization Foundation Model: Tokenizing Graph via A Language-Model Paradigm
arXiv:2509. 24256v2 Announce Type: replace-cross Abstract: The pretrain-transfer paradigm, which underpins the success of large language models (LLMs), has demonstrated the immense power of creating foundation models that learn generalizable representations from vast datasets.
arXiv AI
Jul 14
Uncertainty-guided Compositional Alignment with Part-to-Whole Semantic Representativeness in Hyperbolic Vision-Language Models
arXiv:2603. 22042v3 Announce Type: replace-cross Abstract: While Vision-Language Models (VLMs) have achieved remarkable performance, their Euclidean embeddings remain limited in capturing hierarchical relationships such as part-to-whole or parent-child structures, and often face challenges in multi-object compositional scenarios.