Do Time-Series QA Systems Read the Time Series? Evidence Use and Reasoning Reliability
Research
Research News
New papers, breakthroughs and academic AI research
How Should a Prompt Optimizer Spend a Tight Budget? BudgetAPO with Noise-Adaptive Evaluation
Research
Measurement-First Auditing of Agentic Leaderboards: Contamination Susceptibility, Matched-Control Re-evaluation, and Scorer Validation
Research
Agentic-ZTA: A Multi-Agent Architecture for Autonomous Zero Trust Enforcement
Research
A Testable Theory of Atomic Features
Research
Topology-Conditioned Backdoors: Language Models That Insert Vulnerabilities When They Infer They Are in a Multi-Agent System
Research
DiMOS: Doob-Guided Inference-Time Multi-Objective Search for Scientific Design
Research
Request Order Matters: Cache-History Sensitivity in Selective KV-Cache Reuse for Rolling Agents
Research
Test-Time Adaptation of Reasoning Strategies with Bayesian Nonparametric Memory
Research
Before Agent Tells The Lie: Has Deception Already Been Represented?
Research
Molecules of a Story: Community Detection in PMI-weighted Narrative Networks
Research
Word-Level Text Unmixing via Evidence-Preserving Ownership Routing with Language Models
Research