research note
This paper addresses a structural question in turnstile streaming: when does a space-efficient streaming algorithm implicitly behave like a linear sketch? The classic equivalence of Li–Nguyen–Woodr…
research note
TravelFraudBench (TFG) addresses a critical gap in fraud detection benchmarks by providing a configurable synthetic evaluation framework specifically designed for fraud ring detection in travel pla…
research note
This paper argues that current multi-agent LLM stacks are missing a protocol layer for semantic exchange: not task routing or tool access, but how one agent admits, traces, and stores another agent…
research note
Adversarial Arena tackles a practical bottleneck in post-training LLMs: high-quality, diverse, multi-turn data is expensive to produce, especially in low-resource or safety-critical domains
research note
MANGO addresses inefficiencies in LLM-based web navigation agents that start exploration from the root URL without leveraging global site structure
research note
This paper asks a practical reliability question that most AI-code discussions skip: once an agentic bot opens a pull request, how often does the repository’s CI/CD actually survive the resulting G…
research note
This paper studies a problem that is adjacent to keystroke biometrics but distinct in a crucial way: not “who is typing?” but “is this a human or an injected HID device?” The authors argue that pri…
research note
This paper addresses the challenge of reliable and resource-efficient device authentication in constrained Industrial Internet of Things (IIoT) scenarios using SRAM Physically Unclonable Functions …
research note
This paper argues that a scholar’s published corpus can be mined for a stable reasoning architecture and then reconstituted as a deployable LLM-based “scholar-bot” that performs core academic labor…
research note
HadAgent tackles a specific mismatch in decentralized systems: blockchain consensus consumes computation, while modern LLM-agent serving desperately needs computation that is actually useful
research note
Syn-TurnTurk tackles a very practical bottleneck in spoken dialogue systems: deciding when a Turkish user has actually finished a turn, instead of relying on crude silence thresholds that often mis…
research note
AgentWebBench introduces a first large-scale benchmark specifically designed to evaluate multi-agent coordination in the emerging Agentic Web paradigm, where user agents interact with multiple auto…
