Proof pending. Core topic summary fields are still materializing.
Recent advancements in large language model (LLM) applications are transforming various fields by enhancing task performance and automating complex processes. For instance, KLong introduces a method for solving long-horizon tasks, while CIAO automates software architecture documentation, improving system comprehension. Human-centric topic modeling integrates user goals into topic discovery, and fine-grained contradiction analysis in peer reviews enhances understanding of reviewer disagreements. Additionally, severity-aware optimization in Arabic medical text generation prioritizes critical cases, and reasoning-based occupation recommendations improve job prediction accuracy. These innovations highlight the potential of LLMs to streamline workflows, enhance accuracy, and provide tailored solutions across diverse domains, making them valuable tools for builders seeking efficiency and precision in their projects.
Topic-specific paper and score movement from the daily diff ledger.
This paper introduces KLong, an open-source LLM agent trained to solve extremely long-horizon tasks. The principle is to first cold-start the model via trajectory-splitting SFT, then scale it via prog...
Existing topic modeling methods, from LDA to recent neural and LLM-based approaches, which focus mainly on statistical coherence, often produce redundant or off-target topics that miss the user's unde...
Large language models have shown strong potential for Arabic medical text generation; however, traditional fine-tuning objectives treat all medical cases uniformly, ignoring differences in clinical se...
Laughter is a complex social signal that conveys communicative intent beyond amusement. While prior work has focused on isolated laughter analysis tasks, a comprehensive understanding of laughter in r...
Scientific peer reviews frequently contain conflicting expert judgments, and the increasing scale of conference submissions makes it challenging for Area Chairs and editors to reliably identify and in...
Software architecture documentation is essential for system comprehension, yet it is often unavailable or incomplete. While recent LLM-based techniques can generate documentation from code, they typic...
App store reviews provide a constant flow of real user feedback that can help improve software requirements. However, these reviews are often messy, informal, and difficult to analyze manually at scal...
Estimating the prevalence of a category in a population using imperfect measurement devices (diagnostic tests, classifiers, or large language models) is fundamental to science, public health, and onli...
In this work, we develop a novel reasoning approach to enhance the performance of large language models (LLMs) in future occupation prediction. In this approach, a reason generator first derives a ``r...
This paper introduces the task of analytical question answering over large, semi-structured document collections. We present MuDABench, a benchmark for multi-document analytical QA, where questions re...
Freshness
Canonical route: /topics
Agent Handoff
Canonical ID llm-applications | Route /topic/llm-applications
REST example
curl https://sciencetostartup.com/api/v1/agent-handoff/topic/llm-applicationsMCP example
{
"tool": "search_papers",
"arguments": {
"query": "LLM Applications",
"cluster": "LLM Applications"
}
}source_context
{
"surface": "topic",
"mode": "topic",
"query": "LLM Applications",
"normalized_query": "llm-applications",
"route": "/topic/llm-applications",
"paper_ref": null,
"topic_slug": "llm-applications",
"benchmark_ref": null,
"dataset_ref": null
}Use This Via API or MCP
Topic pages bundle paper counts, viability trends, author concentration, and top questions into one canonical surface your agents can reference before they open Signal Canvas or create a workspace.