arXiv
MNIST-PRO: MNIST is Back as a Partially Observable World for AI Agents
AI agents in partially observable environments need to coordinate active sensing with working memory to maintain an e...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
Measure Before You Manage: Evaluating Agent Working Memory in Coding Agents
Agent working memory is heterogeneous. Objects such as instructions, artifacts, tool outputs, and agent-generated sta...
arXiv
Wrong Prediction, Right Answer: Recovering Evidence from Collapsed LLM Sequence Scores
When a large language model fails a reasoning task, it is often assumed to lack the underlying capability. However, t...
arXiv
Real-Time Video Anomaly Detection Using YOLO Pose Estimation and CLIP-Based Semantic Scoring
We propose a lightweight two-stage framework for real-time video anomaly detection. The first stage employs YOLO v11n...
arXiv
Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence
Recent advances in large reasoning models (LRMs) have shown that reinforcement learning with verifiable rewards (RLVR...
arXiv
Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents
Autonomous scientific research agents are increasingly applied to end-to-end scientific workflows, including literatu...
arXiv
Reconciling Process Supervision with Outcome-Based Credit in Agentic Policy Optimization
Outcome-based reinforcement learning provides verified feedback for language-model agents, but assigns trajectory-lev...
arXiv
Token-Efficient Data Reasoning Agents via Adaptive Structuring of Unstructured Data
Valuable data remains embedded in unstructured sources: web pages, reports, contracts, filings, earnings calls, and P...
arXiv
Cross-Regional Grapevine Cold Hardiness Prediction via Learned Multimodal Latent Representations
Accurate daily predictions of cold hardiness in woody plants are critical in regions where freezing temperatures can ...
arXiv
LLM Post-Training as Brownfield Maintenance: An Industrial Perspective on Dataware Engineering
Industrial post-training is a brownfield regime. Teams inherit a deployed checkpoint and must land targeted improveme...
arXiv
BLOOM-WILT: Logit Tilting for Behaviour Elicitation in Automated LLM Auditing
Users of a deployed language model routinely encounter behaviours that testing almost never surfaces, since deploymen...
arXiv
When Does Bigger Help? A Controlled Study of LLM Scale for Ontology Learning
The effect of Large Language Model (LLM) scale on ontology learning (OL) performance remains insufficiently character...