Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

RASPRef: Retrieval-Augmented Self-Supervised Prompt Refinement for Large Reasoning Models

Rahul Soni

Published

Mar 27, 2026

Citations

0

Trust level

Moderate

Usefulness score

50/100 (Medium)

Extraction confidence

60% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Mar 27, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Critique Edit Long Horizon Math

Should you rely on this paper?

This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.

Use this for comparison and orientation, not as your only source.

Best use

Secondary protocol comparison source

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

No major weakness surfaced.

Human feedback signal
Detected
From extracted signals
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
50/100
Moderate-confidence candidate

Useful as a secondary reference; validate protocol details against neighboring papers.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

Recent reasoning-focused language models such as DeepSeek R1 and OpenAI o1 have demonstrated strong performance on structured reasoning benchmarks including GSM8K, MATH, and multi-hop question answering tasks. However, their performance remains highly sensitive to prompt formulation, and designing effective prompts is typically a manual and iterative process that does not scale well across tasks or domains. To address this limitation, we introduce Retrieval-Augmented Self-Supervised Prompt Refinement (RASPRef), a framework that improves prompts without requiring human annotations or task-specific supervision. The approach retrieves relevant examples and previously generated reasoning trajectories, and leverages signals such as multi-sample consistency, verifier feedback, and model-generated critiques to iteratively refine the prompt. Unlike prior approaches that focus primarily on improving model outputs, RASPRef directly treats the prompt as the optimization target and improves it through an iterative retrieval-guided refinement process. Experiments on GSM8K-style mathematical reasoning tasks show that retrieval-guided prompting improves performance compared with a static prompting baseline. We further discuss how retrieval quality, trajectory selection, and self-supervised feedback signals may influence the effectiveness of prompt refinement. These findings suggest that prompt design remains a critical factor for reasoning-oriented language models, and that self-improving prompts offer a practical and scalable strategy for improving reasoning performance.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

strong

Critique Edit

Directly usable for protocol triage.

"Recent reasoning-focused language models such as DeepSeek R1 and OpenAI o1 have demonstrated strong performance on structured reasoning benchmarks including GSM8K, MATH, and multi-hop question answering tasks."

Evaluation Modes

missing

None explicit

Validate eval design from full paper text.

"Recent reasoning-focused language models such as DeepSeek R1 and OpenAI o1 have demonstrated strong performance on structured reasoning benchmarks including GSM8K, MATH, and multi-hop question answering tasks."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Recent reasoning-focused language models such as DeepSeek R1 and OpenAI o1 have demonstrated strong performance on structured reasoning benchmarks including GSM8K, MATH, and multi-hop question answering tasks."

Benchmarks / Datasets

strong

GSM8K

Useful for quick benchmark comparison.

"Recent reasoning-focused language models such as DeepSeek R1 and OpenAI o1 have demonstrated strong performance on structured reasoning benchmarks including GSM8K, MATH, and multi-hop question answering tasks."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"Recent reasoning-focused language models such as DeepSeek R1 and OpenAI o1 have demonstrated strong performance on structured reasoning benchmarks including GSM8K, MATH, and multi-hop question answering tasks."

Benchmarks and datasets

GSM8K

Reported metrics

No metric terms were extracted from the available abstract.

Human feedback details
Uses human feedback
Yes
Feedback types
Critique Edit
Rater population
Not reported
Unit of annotation
Trajectory
Expertise required
Math
Evaluation details
Evaluation modes
None
Agentic eval
Long Horizon
Quality controls
Not reported
Evidence quality
Moderate
Use this page as
Secondary protocol comparison source

Research brief

Metadata summary

Recent reasoning-focused language models such as DeepSeek R1 and OpenAI o1 have demonstrated strong performance on structured reasoning benchmarks including GSM8K, MATH, and multi-hop question answering tasks.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • Recent reasoning-focused language models such as DeepSeek R1 and OpenAI o1 have demonstrated strong performance on structured reasoning benchmarks including GSM8K, MATH, and multi-hop question answering tasks.
  • However, their performance remains highly sensitive to prompt formulation, and designing effective prompts is typically a manual and iterative process that does not scale well across tasks or domains.
  • To address this limitation, we introduce Retrieval-Augmented Self-Supervised Prompt Refinement (RASPRef), a framework that improves prompts without requiring human annotations or task-specific supervision.

Researcher actions

  • Compare this paper against others mentioning GSM8K.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

GSM8K

Contribution summary

  • Recent reasoning-focused language models such as DeepSeek R1 and OpenAI o1 have demonstrated strong performance on structured reasoning benchmarks including GSM8K, MATH, and multi-hop question answering tasks.
  • To address this limitation, we introduce Retrieval-Augmented Self-Supervised Prompt Refinement (RASPRef), a framework that improves prompts without requiring human annotations or task-specific supervision.

Why it matters for eval

  • Recent reasoning-focused language models such as DeepSeek R1 and OpenAI o1 have demonstrated strong performance on structured reasoning benchmarks including GSM8K, MATH, and multi-hop question answering tasks.
  • To address this limitation, we introduce Retrieval-Augmented Self-Supervised Prompt Refinement (RASPRef), a framework that improves prompts without requiring human annotations or task-specific supervision.

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Critique Edit

  • Evaluation mode is explicit

    No clear evaluation mode extracted.

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    Detected: GSM8K

  • Metric reporting is present

    No metric terms extracted.