Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Video-RSI: Recursive Self-Improvement of Video Understanding Agents via Harness Evolution

Bingjun Luo, Jialin Guo, Siqi Li

Published

Sep 29, 2026

Citations

0

Trust level

Moderate

Usefulness score

65/100 (Medium)

Extraction confidence

70% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Sep 29, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics Coding Critique Edit

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
65/100
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

Video understanding agents acquire evidence through an executable harness that controls what they observe and how they use those observations. However, execution traces contain only the evidence acquired by the current harness, leaving competing explanations for failure unresolved and limiting the basis for self-improvement. We introduce Video-RSI, a framework for recursive self-improvement in which a video understanding agent uses its own language model to revise its harness. Through active video investigation, the model revisits the original training videos to test competing failure explanations with additional observations, grounding proposed changes in evidence beyond the existing trace. Cost-aware harness evolution turns these diagnoses into reusable revisions and determines which revisions to retain by considering both answer accuracy and visual cost. Across our evaluation settings on video understanding benchmarks, the evolved agent improves accuracy while processing fewer frames and achieves competitive accuracy-efficiency trade-offs against existing video understanding agents. These results demonstrate the potential for video understanding agents to improve their own evidence acquisition and use through harness evolution. Code is available at https://github.com/bingjunluo/Video-RSI .

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.

"Video understanding agents acquire evidence through an executable harness that controls what they observe and how they use those observations."

Evaluation Modes

strong

Automatic Metrics

Includes extracted eval setup.

"Video understanding agents acquire evidence through an executable harness that controls what they observe and how they use those observations."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Video understanding agents acquire evidence through an executable harness that controls what they observe and how they use those observations."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Video understanding agents acquire evidence through an executable harness that controls what they observe and how they use those observations."

Reported Metrics

strong

Accuracy

Useful for evaluation criteria comparison.

"Cost-aware harness evolution turns these diagnoses into reusable revisions and determines which revisions to retain by considering both answer accuracy and visual cost."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

accuracy
Human feedback details
Uses human feedback
Yes
Feedback types
Critique Edit
Rater population
Not reported
Expertise required
Coding
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
None
Quality controls
Not reported
Evidence quality
Moderate
Use this page as
Secondary protocol comparison source

Research brief

Metadata summary

Video understanding agents acquire evidence through an executable harness that controls what they observe and how they use those observations.

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

Key takeaways

  • Video understanding agents acquire evidence through an executable harness that controls what they observe and how they use those observations.
  • However, execution traces contain only the evidence acquired by the current harness, leaving competing explanations for failure unresolved and limiting the basis for self-improvement.
  • We introduce Video-RSI, a framework for recursive self-improvement in which a video understanding agent uses its own language model to revise its harness.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Automatic metrics) against the full paper.
  • 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

Accuracy

Contribution summary

  • Video understanding agents acquire evidence through an executable harness that controls what they observe and how they use those observations.
  • We introduce Video-RSI, a framework for recursive self-improvement in which a video understanding agent uses its own language model to revise its harness.
  • Across our evaluation settings on video understanding benchmarks, the evolved agent improves accuracy while processing fewer frames and achieves competitive accuracy-efficiency trade-offs against existing video understanding agents.

Why it matters for eval

  • We introduce Video-RSI, a framework for recursive self-improvement in which a video understanding agent uses its own language model to revise its harness.
  • Across our evaluation settings on video understanding benchmarks, the evolved agent improves accuracy while processing fewer frames and achieves competitive accuracy-efficiency trade-offs against existing video understanding agents.

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Critique Edit

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • 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

    Detected: accuracy