Human Feedback Types
provisional (inferred)None explicit
No explicit feedback protocol extracted.
"Inference-time scaling for LLM reasoning has focused on three axes: chain depth, sample breadth, and learned step-scorers (PRMs)."
HFEPX · Eval paper review
Process Supervision via Verbal Critique Improves Reasoning in Large Language Models
Hao-Yuan Chen
Published
Apr 23, 2026
Citations
0
Trust level
Provisional
Usefulness score
Unavailable
Extraction confidence
0% (Provisional)
Derived from abstract and metadata only.
Signals refreshed
Apr 23, 2026
Should you rely on this paper?
Signal extraction is still processing. This page currently shows metadata-first guidance until structured protocol fields are ready.
This page is a lightweight research summary built from the abstract and metadata while deeper extraction catches up.
Abstract-only analysis, low confidence
All signals on this page are inferred from the abstract only and may be inaccurate. Do not use this page as a primary protocol reference.
- This page is still relying on abstract and metadata signals, not a fuller protocol read.
Best use
Background context only
Use if you need
A provisional background reference while structured extraction finishes.
What to verify
Read the full paper before copying any benchmark, metric, or protocol choices.
Main weakness
This page is still relying on abstract and metadata signals, not a fuller protocol read.
Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Weak or implicit
Validate from full paper
Usefulness for eval research
Unavailable
Provisional (processing)
Eval-fit score is unavailable until extraction completes.
If you are doing eval pipeline work, start here
Abstract
Inference-time scaling for LLM reasoning has focused on three axes: chain depth, sample breadth, and learned step-scorers (PRMs). We introduce a fourth axis, granularity of external verbal supervision, via Verbal Process Supervision (VPS), a training-free framework that uses structured natural-language critique from a stronger supervisor to guide an iterative generate-critique-refine loop up to a round budget R. Across GPQA Diamond, AIME 2025, and LiveCodeBench V6 (covering both closed and open models), VPS yields three key results. First, on GPQA Diamond, GPT-5.4 (High) | GPT-5.4 (Low) reaches 94.9% at R=4, surpassing the 94.1% state of the art without gradient updates. Second, on AIME 2025, VPS enables strong weak-actor rescue, boosting scores from 11.7-26.7% to 63.3-90.0% (up to +63.3 points). Third, at matched compute, VPS outperforms Reflexion by +8.5 to +12.1 points and Self-Consistency@5 by +5.0 pp (GPQA) and +8.3 pp (LiveCodeBench), isolating critique granularity as the key driver. Performance scales with the supervisor-actor capability gap (Pearson r=0.90) and degrades when errors are not linguistically expressible (e.g., code synthesis), motivating hybrid verbal-executable methods. These results establish critique granularity as a new axis of inference-time scaling.
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.
Evaluation Modes
provisional (inferred)None explicit
Validate eval design from full paper text.
"Inference-time scaling for LLM reasoning has focused on three axes: chain depth, sample breadth, and learned step-scorers (PRMs)."
Quality Controls
provisional (inferred)Not reported
No explicit QC controls found.
"Inference-time scaling for LLM reasoning has focused on three axes: chain depth, sample breadth, and learned step-scorers (PRMs)."
Benchmarks / Datasets
provisional (inferred)LiveCodeBench
Useful for quick benchmark comparison.
"Across GPQA Diamond, AIME 2025, and LiveCodeBench V6 (covering both closed and open models), VPS yields three key results."
Reported Metrics
provisional (inferred)Not extracted
No metric anchors detected.
"Inference-time scaling for LLM reasoning has focused on three axes: chain depth, sample breadth, and learned step-scorers (PRMs)."
Rater Population
provisional (inferred)Unknown
Rater source not explicitly reported.
"Inference-time scaling for LLM reasoning has focused on three axes: chain depth, sample breadth, and learned step-scorers (PRMs)."
Human feedback details
This page is using abstract-level cues only right now. Treat the signals below as provisional.
- Potential human-data signal: No explicit human-data keywords detected.
- Potential benchmark anchors: LiveCodeBench
- Abstract highlights: 3 key sentence(s) extracted below.
Evaluation details
Evaluation fields are inferred from the abstract only.
- Potential evaluation modes: No explicit eval keywords detected.
- Potential metric signals: No metric keywords detected.
- Confidence: Provisional (metadata-only fallback).
Research brief
Metadata summary
Inference-time scaling for LLM reasoning has focused on three axes: chain depth, sample breadth, and learned step-scorers (PRMs).
Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.
Key takeaways
- Inference-time scaling for LLM reasoning has focused on three axes: chain depth, sample breadth, and learned step-scorers (PRMs).
- We introduce a fourth axis, granularity of external verbal supervision, via Verbal Process Supervision (VPS), a training-free framework that uses structured natural-language critique from a stronger supervisor to guide an iterative generate-critique-refine loop up to a round budget R.
- Across GPQA Diamond, AIME 2025, and LiveCodeBench V6 (covering both closed and open models), VPS yields three key results.
Researcher actions
- Compare this paper against others mentioning LiveCodeBench.
- 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.