arXiv
Attention-Path Fragility as an Uncertainty Signal in Large Language Models
We propose that a model's uncertainty about a token is reflected not only in the breadth of its output distribution b...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
From Interpretability to Control: Insights from Six Years of the TrustNLP Workshop
The Workshop on Trustworthy Natural Language Processing (TrustNLP), co-located with major ACL conferences since 2021,...
arXiv
How to Verify Consistency of Probabilistic Claims
When a probabilistic predictor answers many conditional-probability queries, are its answers self-consistent, and can...
arXiv
Test-Time Self-Evolving GUI Visual Grounding via Reflection-Guided On-Policy Self-Distillation
GUI Visual Grounding is a fundamental capability for GUI agents. Existing models typically freeze their parameters af...
arXiv
Long-Horizon AI Research for Grothendieck Constant: A Case Study in Human-AI Mathematical Collaboration
AI agents are increasingly used in mathematics research, but it is often unclear how to use them effectively. Towards...
arXiv
ConVAWG: A Retrieval-Grounded Framework for Controlled Synthetic Dialogue Generation in Violence Against Women and Girls
Synthetic dialogue generation offers a way to study conversational dynamics in sensitive domains where real data are ...
arXiv
Surgical WAM: A World-Action Model for Data-Efficient Surgical Robot Learning
Learning reliable surgical manipulation policies is bottlenecked by the scarcity of action-labeled demonstrations: te...
HuggingFace
CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAG
Recent optimization studies on Retrieval-Augmented Generation (RAG) have exploited chunk-level KV cache reuse to avoi...
HuggingFace
VibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World?
Large language model (LLM) agents are increasingly deployed as personal assistants. Existing evaluations, however, mo...
HuggingFace
SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information
Large language models (LLMs) are increasingly deployed as mobile assistants, where a key challenge is leveraging pers...
HuggingFace
DSAgentBench: Can Agents Automate End-to-End Data-Science Workflows in Real Computer Environments?
Real-world data science involves long-horizon workflows that span data wrangling, exploration, modeling, visualizatio...
HuggingFace
Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design
Agentic systems are increasingly expected to improve after deployment, yet single-entity self-evolution is often boun...