Tag
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.