A Conjecture on a Fundamental Trade-Off between Certainty and Scope in Symbolic and Generative AI
arXiv:2506.10130v1 Announce Type: new Abstract: This article introduces a conjecture that formalises a fundamental trade-off between provable correctness and broad…
CoRT: Code-integrated Reasoning within Thinking
arXiv:2506.09820v2 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) like o1 and DeepSeek-R1 have shown remarkable progress in natural language…
VideoDeepResearch: Long Video Understanding With Agentic Tool Using
arXiv:2506.10821v1 Announce Type: cross Abstract: Long video understanding (LVU) presents a significant challenge for current multi-modal large language models (MLLMs)…
What Users Value and Critique: Large-Scale Analysis of User Feedback on AI-Powered Mobile Apps
arXiv:2506.10785v1 Announce Type: cross Abstract: Artificial Intelligence (AI)-powered features have rapidly proliferated across mobile apps in various domains, including productivity,…
Policy-Based Trajectory Clustering in Offline Reinforcement Learning
arXiv:2506.09202v2 Announce Type: replace-cross Abstract: We introduce a novel task of clustering trajectories from offline reinforcement learning (RL) datasets, where…
TIP-Search: Time-Predictable Inference Scheduling for Market Prediction under Uncertain Load
arXiv:2506.08026v1 Announce Type: new Abstract: This paper proposes TIP-Search, a time-predictable inference scheduling framework for real-time market prediction under uncertain…
Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction
arXiv:2506.07976v2 Announce Type: replace-cross Abstract: The current paradigm of test-time scaling relies on generating long reasoning traces (“thinking” more) before…
The impact of fine tuning in LLaMA on hallucinations for named entity extraction in legal documentation
arXiv:2506.08827v1 Announce Type: cross Abstract: The extraction of information about traffic accidents from legal documents is crucial for quantifying insurance…