GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning · HackerPapers discussions

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning — HN submission

Tue, 14 Jul 2026 04:13:02 GMT

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning

4 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning — mentioned by LakshyAAAgrawal

Sun, 22 Feb 2026 05:37:27 GMT

We built optimize_anything, an API that optimizes any artifact representable as text — code, prompts, agent architectures, configs, even SVGs. It extends GEPA (our prompt optimizer, discussed here previously: https://arxiv.org/abs/2507.19457) far beyond prompts. The API is deliberately minimal. You provide what to optimize and how to measure it: import gepa.optimize_anything as oa def evaluate(candidate: str) -> tuple[float, dict]: result = run_my_system(candidate) return result.score, {"error": result.stderr, "runtime": f"{result.time_ms}ms"} result = oa.optimize_anything…

Paper and discussion history. A mention is not an endorsement.

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning — HN submission

Fri, 20 Feb 2026 04:19:04 GMT

Show HN: Optimize_anything: A Universal API for Optimizing Any Text Parameter

8 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning — mentioned by JoshPurtell

Wed, 04 Feb 2026 01:03:15 GMT

For devtools cos providing skills - we've found that using GEPA where you optimize the skill content instead of the prompt works really well to make sure the skill actually gets claude code/ codex /opencode to successfully use your service. https://arxiv.org/abs/2507.19457 More here if interesting https://www.usesynth.ai/blog/environment-pools-managed-agent...

Paper and discussion history. A mention is not an endorsement.

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning — mentioned by deepsquirrelnet

Sun, 19 Oct 2025 19:48:45 GMT

Absolutely the first thing you should try is a prompt optimizer. The GEPA optimizer (implemented in DSPy) often outperforms GRPO training[1]. But I think people are usually building with frameworks that aren't machine learning frameworks. [1] https://arxiv.org/abs/2507.19457

Paper and discussion history. A mention is not an endorsement.

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning — mentioned by Weaver_zhu

Fri, 17 Oct 2025 03:51:54 GMT

I recall recent work [ACE](https://www.arxiv.org/abs/2510.04618) and [GEPA](https://arxiv.org/abs/2507.19457) where models get improved by adapting and adopting different kinds of prompt. The improvements will be expected to be more generalized than fine-tuning.

Paper and discussion history. A mention is not an endorsement.

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning — mentioned by tlarkworthy

Wed, 13 Aug 2025 06:14:02 GMT

Recently tried out the new GEPA algorithm for prompt evolution with great results. I think using LLMs to write their own prompt and analyze their trajectories is pretty neat once appropriate guardrails are in place https://arxiv.org/abs/2507.19457 https://observablehq.com/@tomlarkworthy/gepa I guess GEPA is still preprint and before this survey but I recommend taking a look due to it's simplicity

Paper and discussion history. A mention is not an endorsement.

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning — HN submission

Mon, 28 Jul 2025 05:02:00 GMT

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning

8 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.