[HN Gopher] GEPA: Reflective prompt evolution can outperform rei...
___________________________________________________________________
GEPA: Reflective prompt evolution can outperform reinforcement
learning
Author : che_shr_cat
Score : 84 points
Date : 2025-07-31 10:57 UTC (12 hours ago)
(HTM) web link (arxiviq.substack.com)
(TXT) w3m dump (arxiviq.substack.com)
| ACCount36 wrote:
| And then you use self-distillation to wire the improved prompts
| back into the LLM. Bam, free metacognitive skills.
| falcor84 wrote:
| Self-distillation generally refers to training a smaller model,
| right? I suppose for full metacognition you would use it fine-
| tune the existing model based on its older self?
| ACCount36 wrote:
| No, training a smaller model off a more capable larger model
| (or an ensemble of models) is the "usual" distillation.
|
| "Self-distillation" refers to distilling from a model into a
| copy of itself. Which is of limited use - unless you can
| steer the teacher, and want the student to internalize that
| steering.
|
| The reason for doing self-distillation here is that we have
| both access to a richer representation (logit stream), and
| want to capture a richer behavior - not the answers
| themselves, but better reasoning techniques that are
| downstream from better prompts.
| justanotheratom wrote:
| anyone working on an dspy optimizer for this?
| viksit wrote:
| they've already written one! see omar's x account for details!
| TheTaytay wrote:
| Here's a link to a repost Omar made referencing it:
| https://x.com/DSPyOSS/status/1950733300420510006
| okhat wrote:
| This is a DSPy optimizer, built by the DSPy core team. Just
| wait for open sourcing.
| laughingcurve wrote:
| okhat is a great way to shorten your name gave me a good
| laugh
| barrenko wrote:
| These models / nets / whatever are much "smarter" (loaded term)
| than we think, we just don't know how to plug-in properly yet.
|
| "We are not interested in the fact that the brain has the
| consistency of cold porridge." -- Alan Turing
| quantumHazer wrote:
| This is not how science and engineering work and an arxiv
| should not be taken at face value.
| hnuser123456 wrote:
| It has been commonly observed that the current crop of LLMs
| can be too agreeable/sycophantic (or on some topics, too
| disagreeable) due to the commonly chosen RLHF priorities.
|
| Simply asking the LLM in two separate contexts the same
| question but from opposing perspectives, then in a third
| context asking it to analyze both responses and choose the
| most neutral and objective take, you wipe out any
| "(dis)agreeableness" bias and dig closer to a deeper, more
| nuanced synthesis of a given topic. This paper is just taking
| this idea to the next level.
|
| This isn't really possible with RLHF alone unless you train
| the LLM to often give two opposing perspectives, which would
| get tiring.
| underlines wrote:
| Looking at a Problem from various perspectives, even posing
| ideas, is exactly what reasoning models seem to simulate in
| their thinking CoT to explore the solution space with
| optimizations like MCMC etc.
| ACCount36 wrote:
| A sufficiently capable AI would be able to plug itself in
| properly too.
|
| One more reason to be wary of pushing for better capabilities.
| codekilla wrote:
| I guess Turing couldn't see the trillions of base pairs of DNA,
| complex methylation states, dendritic spines of the neurons,
| etc., just for starters.
| cubefox wrote:
| This summary article is LLM authored [1], but it does seem to
| make sense. HN folks apparently agree, with 58 points for the
| submission so far.
|
| 1: https://arxiviq.substack.com/p/coming-soon
|
| > ArXivIQ exists to turn that fire-hose into jet-streams of
| insight: every paper is hand-picked by a human editor, then
| pushed through a purpose-built multi-agent AI pipeline that
| dissects methods, experiments, and limitations in minutes instead
| of hours.
| strangescript wrote:
| Is the name meant to be a jab at you know who or am I reading too
| much into it?
| kennyadam wrote:
| Why would they want to take a jab at Francis Kojo Kwarteng
| Arthur (Esq), the CEO of Ghana Export Promotion Authority?
| viraptor wrote:
| I have no idea who you mean. Why not just write it?
| bironran wrote:
| To me that's a complete circle back to lessons learned from
| neural networks - I long suspected we'd be heading that way again
| with transformers being a computational step rather than the
| whole thing.
| aseg wrote:
| This is my research area. I just finished reviewing six NeurIPS
| papers (myself, no LLM involved) on LLM Agents for discovery and
| generation and I'm finding that evaluating LLM agents on raw
| performance for a task isn't as insightful anymore -- every paper
| is claiming state of the art 10x performance boost by {insert
| random acronym that devolves into combinatorial search}. Rather
| the true test for such algorithms is whether the empirical
| scaling curves for these algorithms are more computationally
| amenable than an existing baseline search algorithm (like CoT).
|
| Three motivating points:
|
| - GEPA / evolutionary agents are performing a zero-th order (no
| gradient) optimization in a combinatorial space. Their loss
| curves are VERY noisy and stochastic. If we run such agents
| multiple times, the performance variance is extremely high -- and
| in some cases cancels out the gains from single experiment.
| However, obtaining the error bounds is hard because the API costs
| are pretty restrictive.
|
| - The problem we face with test time scaling is not that prompt
| engineering is ineffective/less effective than fine-tuning. It is
| that fine-tuning _reliably_ increases performance for a model for
| any subset of tasks and the scaling curves for performance per
| additional data token are well understood.
|
| - Test time optimization techniques work well on in-distribution
| problems (e.g. generate and debug this Python code) but fail
| pretty badly on even slightly out of distribution problems (e.g.
| generate and debug this Julia code). Compare this to gradient
| search -- it wouldve been so fascinating and confusing if SGD
| failed to optimize a CNN image classifier on COCO but worked very
| well on ImageNet.
|
| How do people feel about this? Does this line up with your
| viewpoints?
| ted_dunning wrote:
| I can't comment on your detailed knowledge of the state of the
| art, but your points resonate (particularly because I have
| tried to generate Julia and Lean code).
|
| So, as with any less informed user reviewing LLM output, what
| you say definitely _sounds_ plausible and correct.
___________________________________________________________________
(page generated 2025-07-31 23:01 UTC)