rrsi alternatives
Curated alternatives to rrsi — and why you'd switch.
sia
Self-improving loop from the SIA paper: Meta, Target and Feedback agents evolve a task agent's harness AND weights against a benchmark — #1 on MLE-Bench Hard, 14x kernel speedups.
Why switchBoth run a meta-loop that evolves a task agent's harness against a benchmark; SIA also trains weights, RRSI keeps the model frozen and regularizes the search so gains survive out of distribution.
Full comparison →JIT
JIT-Agent: a meta-agent that writes a task-specific harness on the fly — memory, planning, action and capability modules emitted as code — and revises it from traces at test time.
Why switchBoth let an LLM rewrite an agent's harness from execution traces; JIT-Agent emits a task-specific harness at test time, RRSI evolves one incumbent harness across rounds with acceptance gates.
Full comparison →SkillOpt
Microsoft's text-space optimizer that trains a frozen agent's skill document like weights — rollouts, bounded edits, validation-gated updates — and ships a compact best_skill.md.
Why switchSame discipline — accept an edit only when held-out evaluation measurably improves; SkillOpt optimizes one skill document, RRSI the whole harness (prompts, control flow, tools, memory).
Full comparison →