MIPROv2
PulseAugur coverage of MIPROv2 — every cluster mentioning MIPROv2 across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
LLM self-improvement loops suffer from 'winner's curse' due to noisy selection
A new arXiv paper explores the phenomenon of "winner's curse" in self-improving Large Language Models (LLMs). The study, which uses Qwen models to rewrite their own instructions, found that most proposed changes after t…
-
DSPy programming framework ported to Elixir for BEAM concurrency
Imp, a new framework, brings the DSPy programming paradigm to the Elixir language and the BEAM virtual machine. This allows developers to build self-improving, declarative language model applications with the reliabilit…
-
CALICO system enhances LLM annotation with editable prompts and new optimizer
Researchers have introduced CALICO, a novel system designed to improve the process of codebook-based annotation for large language models. CALICO treats prompts as editable and optimizable artifacts, allowing domain exp…
-
New benchmark dataset OpenSanctions Pairs released, GPT-4o leads entity matching performance
A new benchmark dataset called OpenSanctions Pairs has been released, designed for large-scale entity matching specifically for sanctions and OSINT data. The dataset contains over 755,000 expert-labeled pairs derived fr…
-
GEPA method optimizes LLM prompts using AI critiques, no GPU needed
A new method called GEPA (Genetic-Pareto Evolutionary Prompt Adaptation) has been introduced, aiming to optimize LLM pipelines without requiring extensive GPU resources for fine-tuning. Developed by researchers from UC …
-
LLM gateway route-switch captures data to optimize prompts
The route-switch LLM gateway, developed by Skelf-Research, offers a novel approach to prompt improvement by capturing and utilizing invocation data. Unlike traditional gateways that merely route requests and discard pro…
-
New framework optimizes LLM agent prompts for information retrieval
Researchers have developed a new iterative prompt optimization framework called Contrastive Reflection, designed to improve the performance of Large Language Model (LLM) agents in information retrieval tasks. This frame…
-
Prompt optimization may weaken LLM adversarial robustness, new benchmark suggests
A new benchmark has been developed to investigate whether prompt optimization techniques for Large Language Models (LLMs) weaken their robustness against adversarial attacks, specifically prompt injection. Initial findi…
-
CANTANTE framework optimizes LLM multi-agent systems via credit attribution
Researchers have developed CANTANTE, a new framework designed to optimize the configuration of large language model-based multi-agent systems. This system addresses the challenge of assigning credit for performance when…
-
Agent Capsules optimize LLM pipelines for efficiency and quality control
Researchers have developed "Agent Capsules," an adaptive runtime system designed to optimize multi-agent large language model (LLM) pipelines. This system addresses the trade-off between token savings from merging agent…