HFEPX · Eval paper review
Xiqi Hao, Zengqing Wu, Yu-Xuan Qiu, Chuan Xiao +3 more
Published
May 30, 2026
Citations
0
Trust level
Moderate
Usefulness score
37/100 (Low)
Extraction confidence
60% (Moderate)
Derived from extracted protocol signals and abstract evidence.
Rater population
Not reported
Signals refreshed
Oct 18, 2026
This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.
Use this for comparison and orientation, not as your only source.
Best use
Background context only
Use if you need
A benchmark-and-metrics comparison anchor.
What to verify
Validate the evaluation procedure and quality controls in the full paper before operational use.
Main weakness
No major weakness surfaced.
Treat as adjacent context, not a core eval-method reference.
If you are doing eval pipeline work, start here
Multi-agent debate (MAD) among large language models (LLMs) is often judged by answer changes and convergence, yet these outcomes alone cannot establish that peers improved the answer. We study this gap with matched self-reflection, stance-only, and full-reasoning conditions. With five GPT-4o agents on MMLU-Pro disagreement questions, 37% of agent-question pairs change even without peer information. Among pairs stable under this control, 29.3% adopt a peer answer after seeing peer stances. These adoptions include corrections, new errors, and changes between wrong answers. The outcomes vary with correct-answer availability. When a correct peer answer is available, correction exceeds harmful adoption after accounting for peer support in the primary setting. Full reasoning improves individual accuracy but provides no additional majority-vote gain over self-reflection while using 57% more tokens. Responses to constructed peer materials vary across GPT-4o, DeepSeek-V4-Flash, and Qwen3-Plus. An answer-agnostic intervention suppresses both harmful and beneficial peer adoption without a detectable accuracy gain. Together, the results show that convergence is an ambiguous signal of value and that debate must be judged by what peer information contributes to the final group answer.
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.
None explicit
No explicit feedback protocol extracted.
"Multi-agent debate (MAD) among large language models (LLMs) is often judged by answer changes and convergence, yet these outcomes alone cannot establish that peers improved the answer."
Llm As Judge, Automatic Metrics
Includes extracted eval setup.
"Multi-agent debate (MAD) among large language models (LLMs) is often judged by answer changes and convergence, yet these outcomes alone cannot establish that peers improved the answer."
Not reported
No explicit QC controls found.
"Multi-agent debate (MAD) among large language models (LLMs) is often judged by answer changes and convergence, yet these outcomes alone cannot establish that peers improved the answer."
MMLU, MMLU Pro
Useful for quick benchmark comparison.
"With five GPT-4o agents on MMLU-Pro disagreement questions, 37% of agent-question pairs change even without peer information."
Accuracy
Useful for evaluation criteria comparison.
"Full reasoning improves individual accuracy but provides no additional majority-vote gain over self-reflection while using 57% more tokens."
Multi-agent debate (MAD) among large language models (LLMs) is often judged by answer changes and convergence, yet these outcomes alone cannot establish that peers improved the answer.
Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.
Human feedback protocol is explicit
No explicit human feedback protocol detected.
Evaluation mode is explicit
Detected: Llm As Judge, Automatic Metrics
Quality control reporting appears
No calibration/adjudication/IAA control explicitly detected.
Benchmark or dataset anchors are present
Detected: MMLU, MMLU-Pro
Metric reporting is present
Detected: accuracy
