Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note3 min read

FinEvo-Bench: A Longitudinal Benchmark for Self-Evolving Agents in Professional Financial Workflows

Source

arXiv

arxiv.org/abs/2608.06144v1

Read the source

Source

Plain-Language Brief

The research introduces a new benchmark called FinEvo-Bench for evaluating the performance of self-evolving agents in professional financial workflows. The benchmark consists of 120 real-case-grounded tasks across six financial domains and includes four different self-evolving agent scaffolds, each with a Qwen3.7-Max backbone. Letta achieved the highest evolved score and fewest compliance issues, while Codex showed the largest self-evolution gain. The study also found that evolving conditions improve scores and reduce compliance issues, and rubric feedback yields higher scores and fewer compliance issues than reference-answer feedback.

What the Document Says

  • FinEvo-Bench is a new longitudinal benchmark for self-evolving agents in professional financial workflows
  • The benchmark consists of 120 real-case-grounded tasks across six financial domains
  • Each task has a manual review rubric for task quality and financial compliance
  • Four different self-evolving agent scaffolds are compared, each with a Qwen3.7-Max backbone
  • Letta achieves the highest evolved score (91.65) and fewest compliance issues (0.09 per task)
  • Codex achieves the largest self-evolution gain (+19.37)
  • The evolving condition raises scores by 9.33-19.37 points and reduces compliance issues by 0.12-0.44 per task
  • Paired score gains at within-scene ranks 4-6 exceed those at ranks 1-3 by 6.10-8.70 points
  • In Claude Code, skill-only evolution produces higher task quality and fewer compliance issues than memory-only and combined memory-skill evolution
  • Across all four scaffolds, rubric feedback also yields higher scores and fewer compliance issues than reference-answer feedback

Key Concepts Mentioned

  • FinEvo-Bench
  • self-evolving agents
  • professional financial workflows
  • benchmark
  • scaffolds
  • Qwen3.7-Max

Claims Made by the Document

  • FinEvo-Bench measures both professional performance and self-evolution ability
  • The evolving condition improves scores and reduces compliance issues
  • Rubric feedback yields higher scores and fewer compliance issues than reference-answer feedback

Evidence Used

  • The description of FinEvo-Bench as a benchmark for measuring both professional performance and self-evolution ability
  • The reported improvements in scores and reduction in compliance issues with the evolving condition
  • The comparison of rubric feedback to reference-answer feedback and their respective impacts on scores and compliance issues

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Most agent benchmarks evaluate tasks independently and cannot measure whether experience from one task helps with later tasks. Existing self-evolution benchmarks do not jointly cover professional workflows, open-ended deliverables, and multi-aspect evaluation. We introduce FinEvo-Bench, a longitudinal benchmark with 120 real-case-grounded tasks, 20 business scenes across six financial domains. Institution-provided professional procedures define the required operations and constraints. Eligible institution-provided and publicly documented cases supply the task facts. Each scene contains six related but substantively distinct cases that share a professional procedure and a manually reviewed rubric for task quality and financial compliance. We compare four self-evolving agent scaffolds using the same Qwen3.7-Max backbone and three independently shuffled, globally interleaved task streams. Paired non-evolving controls estimate each scaffold's self-evolution gain from retained experience, while an independent Claude Code scoring agent backed by Claude Opus 4.6 evaluates all outputs. Letta achieves the highest evolved score (91.65) and fewest compliance issues (0.09 per task); Codex achieves the largest self-evolution gain (+19.37). Across scaffolds, the evolving condition raises scores by 9.33-19.37 points and reduces compliance issues by 0.12-0.44 per task. Paired score gains at within-scene ranks 4-6 exceed those at ranks 1-3 by 6.10-8.70 points. In Claude Code, skill-only evolution produces higher task quality and fewer compliance issues than memory-only and combined memory-skill evolution. Across all four scaffolds, rubric feedback also yields higher scores and fewer compliance issues than reference-answer feedback. FinEvo-Bench measures both professional performance and self-evolution ability: how effectively an agent turns prior experience into later improvement.