performance
6 notes, newest first.
Can Agent Harnesses and Inference Engines Hear Each Other? The HEAR Protocol for Agentic LLM Serving
The preprint proposes HEAR, a bidirectional Harness–Engine Pairing protocol that lets an agent harness communicate workflow intent and execution requirements while the inference engine returns runtime state…
An Inclusive and Lightweight Approach to Federated Continual Learning for Cultural Heritage
The authors propose a lightweight approach to Federated Continual Learning (FCL) called FedCurv-DR for supporting artificial intelligence in cultural heritage. This method is designed to learn from distributed and…
VAKRA: Evaluating Multi-Hop Reasoning Across APIs and Retrieval Under Tool-Use Policies
The researchers introduce VAKRA, a benchmark for evaluating the ability of agents to reason across structured APIs and document collections in enterprise settings. The benchmark includes over 8,000 executable APIs…
ORCA-bench: How Ready Are Language Model Agents for Oncall?
The study presents ORCA-bench, a benchmark for evaluating the performance of large language models in oncall root cause analysis (RCA). The benchmark exposes a microservice system with six days of data and 1,079 RCA…
LLM-as-a-Verifier: A General-Purpose Verification Framework
Researchers introduce a new framework called LLM-as-a-Verifier to improve the ability of Large Language Models (LLMs) to verify the correctness of solutions for various tasks. The method provides fine-grained feedback…
Program-as-Weights: A Programming Paradigm for Fuzzy Functions
The authors propose a new programming paradigm called fuzzy-function programming, where functions can be compiled from natural language specifications into compact, locally executable neural networks. They introduce…
