ComplianceGate: Classifier-Gated Multi-Tier LLM Routing for Inference in Regulated Industries
arXiv:2606.31163v2 Announce Type: replace-cross Abstract: Large language models deployed in regulated industries operate under two constraints: compliance enforcement and cost…
Empowering biomedical evidence exploration and synthesis with deep knowledge graph research
Nature Machine Intelligence, Published online: 02 July 2026; doi:10.1038/s42256-026-01266-0 Wang et al. develop DeepEvidence, a biomedical deep research agent for…
Reshaping biomolecular structure prediction through strategic conformational exploration with HelixFold-S1
Nature Machine Intelligence, Published online: 02 July 2026; doi:10.1038/s42256-026-01264-2 Liu and colleagues introduce HelixFold-S1, a guided sampling strategy for biomolecular…
What Drives Interactive Improvement from Feedback?
arXiv:2606.30774v1 Announce Type: new Abstract: We study when natural-language feedback produces improvement beyond the gains obtainable from repeated attempts alone.…
TraceLab: Characterizing Coding Agent Workloads for LLM Serving
arXiv:2606.30560v2 Announce Type: replace-cross Abstract: Coding agents are rapidly becoming a major application of agentic LLMs, but serving them efficiently…
Improving multichannel speech enhancement through accurate room-acoustic simulations
arXiv:2606.31552v1 Announce Type: cross Abstract: Room-acoustic simulations are widely used to augment training data for deep-learning-based speech enhancement. While most…
On the Convergence of Self-Improving Online LLM Alignment
arXiv:2606.31524v1 Announce Type: cross Abstract: The Self-Improving Alignment (SAIL) algorithm addresses distribution shift by reducing a bilevel formulation of the…
TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation
arXiv:2606.29575v2 Announce Type: replace-cross Abstract: Recent advances in speech separation (SS) have led to compact front-end models with small parameter…
Recursive Self-Evolving Agents via Held-Out Selection
arXiv:2606.28374v1 Announce Type: new Abstract: LLM agents are increasingly improved without weight updates by evolving a natural-language artifact, such as…
Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models
arXiv:2606.28153v2 Announce Type: replace-cross Abstract: Jailbreak attacks bypass LLM safety alignment, yet their mechanisms remain poorly understood. We provide evidence…