6 projects
toolform
Tool interfaces for LLM agents, chosen by measurement: recommend, render, parse and guard the tool block from a study of 129 formats, 31 answer protocols and 112 models.
pyragx
Agentic retrieval at scale: an agent ranks and reads passages, a chain of sub-questions names the evidence the question leaves unnamed, and one call answers with exact citations.
effgen
A comprehensive framework for building agents with Small Language Models
beyondbench
BeyondBench: Contamination-Resistant Evaluation of Reasoning in Language Models
llmthinkbench
A framework for evaluating overthinking and basic reasoning capabilities of Large Language Models
genetic-optimization
Genetic Optimization package
