arXiv:2609.26986v1 Announce Type: new Abstract: For multimodal large language models, when images or speech conflict with accompanying text, measured text…
Tag: AI
Training Intelligent Voice Assistant Wakeup with Controllable Synthetic Conversations
arXiv:2609.27037v1 Announce Type: new Abstract: Wake word detection is a critical component of virtual assistants, serving as the gateway to seamless user…
Reinforcement Learning with Decomposed Subtasks
arXiv:2609.27035v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) and related policy-gradient methods for training language model…
Building Socio-Affective Artificial Intelligence for Interactive Multi-Agent Simulations
arXiv:2609.26927v1 Announce Type: new Abstract: The objective of this article is to provide design principles and a software architecture for enabling…
Which Objectives Need a Dial? Predicting Objective Conflict and Covering Trade-offs in Steerable Pluralistic Alignment
arXiv:2609.26929v1 Announce Type: new Abstract: People hold diverse, sometimes conflicting values, so no single aligned model can satisfy everyone.…
Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity
arXiv:2609.26891v1 Announce Type: new Abstract: Modern language-model agents are built around the \textit{agent loop}, where the LLM is placed in an…
TwinCheck: Evidence-Grounded Negative-Twin Verification for Stateful Tool Agents
arXiv:2609.26911v1 Announce Type: new Abstract: A single locally plausible tool call can derail an otherwise successful agent trajectory. Suspicion alone…
Silent Failures in Agent-Tool Interaction: An Audit of ToolUniverse
arXiv:2609.26836v1 Announce Type: new Abstract: Agentic AI systems are increasingly adopting automated pipelines that integrate multiple tools. While…
EquiSELD: Efficient training of equivariant sound event localization and detection networks
arXiv:2609.23156v1 Announce Type: cross Abstract: First-order Ambisonics (FOA) signals exhibit exact O(3) symmetry: The rotation or reflection of the FOA…
Why Ghost Outputs Teach: A Kernel-Based Understanding of Subliminal Learning
arXiv:2609.23260v1 Announce Type: cross Abstract: Subliminal Learning (SL) is a recently identified phenomenon in which a student model acquires…