Check out Speculative Programmatic Tool Calling (sPTC) for a fresh approach to harness optimization, offering significant speedup compared to traditional methods. It's a must-read for those interested in RLM and harness efficiency.
Speculative Programmatic Tool Calling (sPTC) is a new technique for optimizing harness designs in code generation, offering 1 to 1.2x speedup by overlapping tool calls with token generation. It's developed by the same author as RLM and aims to improve efficiency at the harness layer.
Recommended reading and a really cool idea. There are a lot of interesting harness designs that ar...
Recommended reading and a really cool idea. There are a lot of interesting harness designs that are starting to emerge around tool calling and code execution. RLM is one of them. But so is this Speculative Programmatic Tool Calling approach (from the same author of RLM). There are plenty of ways to gain efficiencies at the harness layer. Harnesses make agents wait: the model streams a block of code, and tool calls inside it only run once generation finishes. sPTC launches the safe calls early against a copy of the environment, so tool latency overlaps with token generation instead of adding on top of it. Bad guesses get thrown away. So far it's 1 to 1.2x speedup. Very promising. alex zhang @a1zhang Introducing Speculative Programmatic Tool Calling (sPTC)! A general class of technique for speculating on tool calls during code generation in a harness and queuing them early to overlap with token generation + REPL execution time. Blog: alexzhang13.github.io/blog/2026/spec… 🔗 View Quoted Tweet 💬 2 🔄 2 ❤️ 18 👀 3421 📊 5 ⚡