SUPER INTELLIGENCE BREAK
A focused stream of intelligence from the sources you trust.
arXiv:2610.24164v1 Announce Type: new Abstract: Voice agents built as cascaded automatic speech recognition (ASR)->large language model (LLM)-> text-to-speech (TTS) pipelines increasingly rely on conversational TTS: streaming, context conditioned models that adapt delivery to dialogue…
arXiv:2603.19921v2 Announce Type: replace Abstract: Machine Translation (MT) and automatic MT evaluation have improved dramatically in recent years, enabling numerous novel applications. Automatic evaluation techniques have evolved from producing scalar quality scores to precisely…
arXiv:2610.24157v1 Announce Type: new Abstract: We present CoDA, an open-source human-LM collaborative codebook development assistant that helps domain experts develop annotation guidelines for annotating new variables in unstructured text with language models. Existing language…
arXiv:2610.26659v1 Announce Type: cross Abstract: Spatial intelligence requires agents to actively acquire visual evidence and integrate observations into a coherent representation of the three-dimensional world. Yet spatial question answering offers limited evidence of whether…
arXiv:2610.24150v1 Announce Type: new Abstract: Everyday norms of social interaction – e.g. norms of sharing space, taking turns, or queuing – are essential to large societies, offering structured procedures for common interactions. However, it…
arXiv:2610.26035v1 Announce Type: cross Abstract: Decision models, such as the commercial Jev, are language models that return one probability for each option of a question instead of generating text. We present Decision4Rec, an open…
arXiv:2610.23868v1 Announce Type: new Abstract: Machine translation systems often preserve meaning but systematically flatten linguistic style, a failure that is most acute when translating into non-Western languages. The RASTA framework of Havaldar et al.…
arXiv:2610.24048v1 Announce Type: new Abstract: LLM agents that read untrusted content can be hijacked by prompt injections. Runtime monitors that try to catch a hijack before the agent acts, and benchmarks that score each…
arXiv:2610.24050v1 Announce Type: new Abstract: As automated research is increasingly adopted for writing papers, automated review has become a critical link between paper generation and quality control. However, existing methods largely rely on single-model…
arXiv:2610.24118v1 Announce Type: new Abstract: Variable roles describe recurring behaviors such as accumulation, traversal, and retaining the best candidate encountered. We use Sajaniemi's independently defined taxonomy to study which role distinctions can be recovered…
arXiv:2610.24087v1 Announce Type: new Abstract: Can large language model (LLM) agents deliver expert-level operations research (OR) solutions directly from original client materials, without prior expert reformulation? Existing OR benchmarks typically begin with self-contained descriptions…
arXiv:2507.03949v2 Announce Type: replace Abstract: Person descriptions in public-safety text can be compact and regular, or distributed across heterogeneous narratives in which evidence boundaries and person ownership are ambiguous. We present POSID, a target-task-unsupervised…