Tag
MaSCoD is a multi-agent framework that pre-organizes structural hypotheses before direct-edge judgment to improve retention of potentially relevant causal relations in candidate graph generation, evaluated on datasets using GPT-5.4 and GPT-4o.
The study presents a digital twin framework using Mistral-7B to simulate opinion dynamics in social networks, validated against real Twitter datasets with over 50% improvement in prediction accuracy compared to classical baselines.
CliniCIRCA is a multi-stage LLM framework for reconstructing longitudinal mental health patient journeys from unstructured EHR narratives, achieving temporal classification without event-level timestamps and using clinician-in-the-loop evaluation for verification.
CDEP Agent is an auditable LLM-agent framework that connects meteorologically detected compound drought-to-extreme-precipitation events to real-world documentary evidence, revealing that most such events go undocumented in current reporting systems.
ATOM is an open-source, self-hosted AI agent platform designed with governed autonomy and verified outcomes to help AI agents move from pilots to production successfully.
ASTAR is an LLM-based framework that automates the induction of standardized radiology reporting templates from large-scale clinical free-text corpora, reducing manual effort and improving template quality compared to expert-curated methods.
This blog post introduces LEVI, a framework for AI-driven research for systems (ADRS) that reduces the cost of algorithmic discovery by using smaller models for most mutations and reserving large models for paradigm shifts, achieving 3-7x cost reduction. It argues that ADRS should be integrated into CI/CD for continuous, bespoke optimization per deployment.
Ax is a JS/TS library providing high-level abstractions for LLM usage (signatures, agents, flows, optimizers). It now introduces axIR, allowing compilation to Python, Java, C++, and Go, making the same programming model available across multiple languages.
This paper introduces AHD Agent, a framework using agentic reinforcement learning to enable LLMs to autonomously design heuristics for combinatorial optimization problems by dynamically interacting with the solving environment.
DSPy 3.2.0 improves dspy.RLM parsing, tool execution, and failure recovery, plus ongoing work to decouple from LiteLLM.
SwanNLP presents an LLM-based framework for plausibility scoring in narrative word sense disambiguation at SemEval-2026 Task 5, using structured reasoning and dynamic few-shot prompting to predict human-perceived plausibility of word senses in short stories. The work demonstrates that commercial large-parameter LLMs with few-shot prompting and model ensembling effectively replicate human judgment patterns in realistic narrative contexts.
A working reference implementation of context engineering — a discipline for designing, retrieving, and injecting organizational context into AI systems to produce accurate, domain-specific outputs. The repo demonstrates five components (corpus, retrieval, injection, output, enforcement) running against Amazon Bedrock with Claude.