HFEPX · Eval paper review
Jiaqi Su, Guibin Zhang, Jie-Jing Shao, Cong Pang +4 more
Published
Oct 18, 2026
Citations
0
Trust level
Moderate
Usefulness score
25/100 (Low)
Extraction confidence
55% (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
Model--harness co-evolution has emerged as a prominent paradigm for recursive self-improving (RSI) agents, jointly evolving their execution scaffolds and intrinsic capabilities. We study the persistent yet often overlooked brain--body mismatch problem in this paradigm, where an evolving harness (body) demands behaviors its model (brain) has not learned or restricts capabilities it already possesses. We introduce CoEvo-RSI, a RSI framework that advances model--harness co-evolution through agent-driven, bidirectional historical inheritance. Drawing on a shared evolutionary archive and execution feedback, a meta-agent coordinates harness development from historical designs with model checkpoint selection or merging and subsequent adaptation under the selected harness, aligning inherited capabilities with evolving execution requirements to reduce brain--body mismatch. Using only supervised fine-tuning (SFT) on its own rejection-sampled trajectories, CoEvo-RSI makes Qwen3.5-9B competitive with larger models across diverse vertical applications, including multi-agent failure attribution, role-aware text-to-SQL, and smart-home instruction following. It surpasses DeepSeek-V4-Pro on TraceElephant (+14.16 agent accuracy) and GLM-5.3 on HomeBench VM (+4.90 success rate), underscoring the need for brain--body alignment and the potential of bidirectional historical inheritance to advance agent co-evolution.
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.
"Model--harness co-evolution has emerged as a prominent paradigm for recursive self-improving (RSI) agents, jointly evolving their execution scaffolds and intrinsic capabilities."
Automatic Metrics
Includes extracted eval setup.
"Model--harness co-evolution has emerged as a prominent paradigm for recursive self-improving (RSI) agents, jointly evolving their execution scaffolds and intrinsic capabilities."
Not reported
No explicit QC controls found.
"Model--harness co-evolution has emerged as a prominent paradigm for recursive self-improving (RSI) agents, jointly evolving their execution scaffolds and intrinsic capabilities."
Homebench
Useful for quick benchmark comparison.
"It surpasses DeepSeek-V4-Pro on TraceElephant (+14.16 agent accuracy) and GLM-5.3 on HomeBench VM (+4.90 success rate), underscoring the need for brain--body alignment and the potential of bidirectional historical inheritance to advance agent co-evolution."
Accuracy, Success rate
Useful for evaluation criteria comparison.
"It surpasses DeepSeek-V4-Pro on TraceElephant (+14.16 agent accuracy) and GLM-5.3 on HomeBench VM (+4.90 success rate), underscoring the need for brain--body alignment and the potential of bidirectional historical inheritance to advance agent co-evolution."
Model--harness co-evolution has emerged as a prominent paradigm for recursive self-improving (RSI) agents, jointly evolving their execution scaffolds and intrinsic capabilities.
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: Automatic Metrics
Quality control reporting appears
No calibration/adjudication/IAA control explicitly detected.
Benchmark or dataset anchors are present
Detected: Homebench
Metric reporting is present
Detected: accuracy, success rate
