Actualités
Agentic Jigsaw Interaction Learning for Enhancing Visual Perception and Reasoning in Vision-Language Models
arXiv:2510.01304v1 Announce Type: cross Abstract: Although current large Vision-Language Models (VLMs) have advanced in multimodal...
Agentic Context Engineering (ACE): Self-Improving LLMs via Evolving Contexts, Not Fine-Tuning
TL;DR: A team of researchers from Stanford University, SambaNova Systems and UC Berkeley introduce ACE...
AgentCompass: Towards Reliable Evaluation of Agentic Workflows in Production
arXiv:2509.14647v1 Announce Type: cross Abstract: With the growing adoption of Large Language Models (LLMs) in...
AgentArmor: Enforcing Program Analysis on Agent Runtime Trace to Defend Against Prompt Injection
arXiv:2508.01249v1 Announce Type: cross Abstract: Large Language Model (LLM) agents offer a powerful new paradigm...
Agentar-Fin-R1: Enhancing Financial Intelligence through Domain Expertise, Training Efficiency, and Advanced Reasoning
arXiv:2507.16802v2 Announce Type: replace Abstract: Large Language Models (LLMs) exhibit considerable promise in financial applications;...
Agent0: A Fully Autonomous AI Framework that Evolves High-Performing Agents without External Data through Multi-Step Co-Evolution
Large language models need huge human datasets, so what happens if the model must create...
Agent-based computing is outgrowing the web as we know it
AI agents are moving from passive assistants to active participants. Today, we ask them to...
Agent Learning via Early Experience
arXiv:2510.08558v2 Announce Type: replace-cross Abstract: A long-term goal of language agents is to learn and...
AegisLLM: Scaling LLM Security Through Adaptive Multi-Agent Systems at Inference Time
The Growing Threat Landscape for LLMs LLMs are key targets for fast-evolving attacks, including prompt...
Adversarial Topic-aware Prompt-tuning for Cross-topic Automated Essay Scoring
arXiv:2508.05987v1 Announce Type: new Abstract: Cross-topic automated essay scoring (AES) aims to develop a transferable...
Advancing Single and Multi-task Text Classification through Large Language Model Fine-tuning
arXiv:2412.08587v2 Announce Type: replace Abstract: Both encoder-only models (e.g., BERT, RoBERTa) and large language models...
ADORE: Autonomous Domain-Oriented Relevance Engine for E-commerce
arXiv:2512.02555v1 Announce Type: new Abstract: Relevance modeling in e-commerce search remains challenged by semantic gaps...
