HFEPX · Eval paper review
Hexuan Deng, Wenxiang Jiao, Xuebo Liu, Jun Rao +1 more
Published
May 26, 2025
Citations
0
Trust level
Low
Usefulness score
40/100 (Low)
Extraction confidence
45% (Low)
Derived from extracted protocol signals and abstract evidence.
Rater population
Not reported
Signals refreshed
Feb 27, 2026
This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.
Use this as background context only. Do not make protocol decisions from this page alone.
Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.
Best use
Background context only
Use if you need
Background context only.
What to verify
Read the full paper before copying any benchmark, metric, or protocol choices.
Main weakness
The available metadata is too thin to trust this as a primary source.
Treat as adjacent context, not a core eval-method reference.
If you are doing eval pipeline work, start here
Large Reasoning Models (LRMs) demonstrate strong performance in complex tasks but often face the challenge of overthinking, leading to substantially high inference costs. Existing approaches synthesize shorter reasoning responses for LRMs to learn, but are inefficient for online usage due to the time-consuming data generation and filtering processes. Meanwhile, online reinforcement learning mainly adopts a length reward to encourage short reasoning responses, but it tends to lose reflection ability and harm performance. To address these issues, we propose REA-RL, which introduces a small reflection model for efficient scaling in online training, offering both parallel sampling and sequential revision. Besides, a reflection reward is designed to further prevent LRMs from favoring short yet non-reflective responses. Experiments show that both methods maintain or enhance performance while significantly improving inference efficiency. Their combination achieves a good balance between performance and efficiency, reducing inference costs by 36% without compromising performance. Further analysis demonstrates that our methods are effective by maintaining reflection frequency for hard problems while appropriately reducing it for easier ones without losing reflection ability. Code is available at https://github.com/hexuandeng/REA-RL.
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.
Critique Edit
Directly usable for protocol triage.
"Large Reasoning Models (LRMs) demonstrate strong performance in complex tasks but often face the challenge of overthinking, leading to substantially high inference costs."
None explicit
Validate eval design from full paper text.
"Large Reasoning Models (LRMs) demonstrate strong performance in complex tasks but often face the challenge of overthinking, leading to substantially high inference costs."
Not reported
No explicit QC controls found.
"Large Reasoning Models (LRMs) demonstrate strong performance in complex tasks but often face the challenge of overthinking, leading to substantially high inference costs."
Not extracted
No benchmark anchors detected.
"Large Reasoning Models (LRMs) demonstrate strong performance in complex tasks but often face the challenge of overthinking, leading to substantially high inference costs."
Not extracted
No metric anchors detected.
"Large Reasoning Models (LRMs) demonstrate strong performance in complex tasks but often face the challenge of overthinking, leading to substantially high inference costs."
No benchmark or dataset names were extracted from the available abstract.
No metric terms were extracted from the available abstract.
Large Reasoning Models (LRMs) demonstrate strong performance in complex tasks but often face the challenge of overthinking, leading to substantially high inference costs.
Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.
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
No benchmark/dataset anchor extracted from abstract.
Metric reporting is present
No metric terms extracted.
