Yes, I’m the author of this paper. One correction: the paper is inaccurate on this point. If you look at the implementation(https://github.com/agentconnect-md/lsp-vs-grep-token-study/b...), the harness is actually based…
I had a similar intuition that we could definitely optimize token efficiency and performance for non-general tasks. For example, I was handling a lot of infra operations, many of which follow fixed workflows like…
Interesting tool, it seems that dedicated skills for these tools are important. Even explicit system-prompt instructions—such as “you must use tool X for code exploration”—often fail to behave as expected. Another…
I am thinking of where the initial training data came from. For example, Claude Code likely collected a substantial number of real-world coding trajectories through its CLI. However, trajectories involving tools such as…
Yes, I’m the author of this paper. One correction: the paper is inaccurate on this point. If you look at the implementation(https://github.com/agentconnect-md/lsp-vs-grep-token-study/b...), the harness is actually based…
I had a similar intuition that we could definitely optimize token efficiency and performance for non-general tasks. For example, I was handling a lot of infra operations, many of which follow fixed workflows like…
Interesting tool, it seems that dedicated skills for these tools are important. Even explicit system-prompt instructions—such as “you must use tool X for code exploration”—often fail to behave as expected. Another…
I am thinking of where the initial training data came from. For example, Claude Code likely collected a substantial number of real-world coding trajectories through its CLI. However, trajectories involving tools such as…