arXiv:2604.07595v1 Announce Type: new Abstract: Language model agents reason from scratch on every query: each time an agent retrieves evidence and deliberates, the chain of thought is discarded and the next similar query starts with no prior insight. This produces lower accuracy and high variance, as the same type of query can succeed or fail […]
EMSDialog: Synthetic Multi-person Emergency Medical Service Dialogue Generation from Electronic Patient Care Reports via Multi-LLM Agents
arXiv:2604.07549v1 Announce Type: cross Abstract: Conversational diagnosis prediction requires models to track evolving evidence in streaming clinical conversations and decide when to commit to a diagnosis. Existing medical dialogue corpora are largely dyadic or lack the multi-party workflow and annotations needed for this setting. We introduce an ePCR-grounded, topic-flow-based multi-agent generation pipeline that iteratively plans, […]
A Machine Learning Framework for Turbofan Health Estimation via Inverse Problem Formulation
arXiv:2604.08460v1 Announce Type: cross Abstract: Estimating the health state of turbofan engines is a challenging ill-posed inverse problem, hindered by sparse sensing and complex nonlinear thermodynamics. Research in this area remains fragmented, with comparisons limited by the use of unrealistic datasets and insufficient exploration of the exploitation of temporal information. This work investigates how to […]
Generative Experiences for Digital Mental Health Interventions: Evidence from a Randomized Study
arXiv:2604.07558v1 Announce Type: cross Abstract: Digital mental health (DMH) tools have extensively explored personalization of interventions to users’ needs and contexts. However, this personalization often targets what support is provided, not how it is experienced. Even well-matched content can fail when the interaction format misaligns with how someone can engage. We introduce generative experience as […]
PRIME: Training Free Proactive Reasoning via Iterative Memory Evolution for User-Centric Agent
arXiv:2604.07645v1 Announce Type: new Abstract: The development of autonomous tool-use agents for complex, long-horizon tasks in collaboration with human users has become the frontier of agentic research. During multi-turn Human-AI interactions, the dynamic and uncertain nature of user demands poses a significant challenge; agents must not only invoke tools but also iteratively refine their understanding […]
DCD: Domain-Oriented Design for Controlled Retrieval-Augmented Generation
arXiv:2604.07590v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) is widely used to ground large language models in external knowledge sources. However, when applied to heterogeneous corpora and multi-step queries, Naive RAG pipelines often degrade in quality due to flat knowledge representations and the absence of explicit workflows. In this work, we introduce DCD (Domain-Collection-Document), a […]
SIM1: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worlds
arXiv:2604.08544v1 Announce Type: cross Abstract: Robotic manipulation with deformable objects represents a data-intensive regime in embodied learning, where shape, contact, and topology co-evolve in ways that far exceed the variability of rigids. Although simulation promises relief from the cost of real-world data acquisition, prevailing sim-to-real pipelines remain rooted in rigid-body abstractions, producing mismatched geometry, fragile […]
Towards Real-Time Human-AI Musical Co-Performance: Accompaniment Generation with Latent Diffusion Models and MAX/MSP
arXiv:2604.07612v1 Announce Type: cross Abstract: We present a framework for real-time human-AI musical co-performance, in which a latent diffusion model generates instrumental accompaniment in response to a live stream of context audio. The system combines a MAX/MSP front-end-handling real-time audio input, buffering, and playback-with a Python inference server running the generative model, communicating via OSC/UDP […]
How Independent are Large Language Models? A Statistical Framework for Auditing Behavioral Entanglement and Reweighting Verifier Ensembles
arXiv:2604.07650v1 Announce Type: new Abstract: The rapid growth of the large language model (LLM) ecosystem raises a critical question: are seemingly diverse models truly independent? Shared pretraining data, distillation, and alignment pipelines can induce hidden behavioral dependencies, latent entanglement, that undermine multi-model systems such as LLM-as-a-judge pipelines and ensemble verification, which implicitly assume independent signals. […]
Safe Large-Scale Robust Nonlinear MPC in Milliseconds via Reachability-Constrained System Level Synthesis on the GPU
arXiv:2604.07644v1 Announce Type: cross Abstract: We present GPU-SLS, a GPU-parallelized framework for safe, robust nonlinear model predictive control (MPC) that scales to high-dimensional uncertain robotic systems and long planning horizons. Our method jointly optimizes an inequality-constrained, dynamically-feasible nominal trajectory, a tracking controller, and a closed-loop reachable set under disturbance, all in real-time. To efficiently compute […]
Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM Reasoning
arXiv:2602.03249v2 Announce Type: replace Abstract: Scaling test-time compute via long Chain-of-Thought unlocks remarkable gains in reasoning capabilities, yet it faces practical limits due to the linear growth of KV cache and quadratic attention complexity. In this paper, we introduce Accordion-Thinking, an end-to-end framework where LLMs learn to self-regulate the granularity of the reasoning steps through […]
Reinforcement Learning with LLM-Guided Action Spaces for Synthesizable Lead Optimization
arXiv:2604.07669v1 Announce Type: cross Abstract: Lead optimization in drug discovery requires improving therapeutic properties while ensuring that proposed molecular modifications correspond to feasible synthetic routes. Existing approaches either prioritize property scores without enforcing synthesizability, or rely on expensive enumeration over large reaction networks, while direct application of Large Language Models (LLMs) frequently produces chemically invalid […]