arXiv:2608.14354v1 Announce Type: new Abstract: Enabling LLM agents to sustain productive, stable, and goal-aligned research over extended horizons is a…
Category: AI
Wrong but Useful: Trajectory Value Beyond Answer Correctness in Multi-Agent Messages
arXiv:2608.14375v1 Announce Type: new Abstract: Multi-agent reasoning systems often use agreement, confidence, or automated scores to decide which…
Designing Sustainable Federated Learning as a Service using Neural Architecture Search
arXiv:2608.14359v1 Announce Type: new Abstract: The sustainability constraints of FLaaS consumers pose significant challenges to maintaining…
Sensor-Driven Mission Synthesis for UAV/UGV Swarms: A TB-CSPN Coordination Architecture with Hardware-Enforced Safety
arXiv:2608.14306v1 Announce Type: new Abstract: This paper presents a coordination architecture for heterogeneous UAV/UGV swarms that synthesises mission…
Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning
arXiv:2608.14290v1 Announce Type: new Abstract: We introduce Mobius-v0, an architecture that comprises a globally shared Memory (FFN) that stores…
Program-space Diffusion for Morphology-to-Transcriptomics Prediction
arXiv:2608.14330v1 Announce Type: new Abstract: Spatial transcriptomics (ST) enables genome-wide gene expression profiling while preserving tissue…
TimeSage-EV: A Live Benchmark for Agentic Time Series Analysis in Evolving Environments
arXiv:2608.14270v1 Announce Type: new Abstract: Time series analysis in high-stakes domains relies on recurring data releases, where new observations can…
Kamya Elawadhi, Co-founder and President of Doceree – Interview Series
Kamya Elawadhi, Co-founder and President of Doceree, is a healthcare marketing and business strategy executive who has played a central role in the…
AnchorBench: A Multi-Pathway Benchmark for the Anchoring Effect in LLMs
arXiv:2608.14320v1 Announce Type: new Abstract: The anchoring effect is a cognitive bias in which an initial reference value shifts a later judgment…
Grounding Without Corrective Control: Truth-Tracking Profiles for Large Language Models
arXiv:2608.14252v1 Announce Type: new Abstract: Recent work suggests that some large language model representations have content or reference. Grounding…