Phantom Guardrails: When Self-Improving Agent Harnesses Fix Failures That Never Happened — AI agent app

Su Wang, Pin Qian, Yifan Lin, Jingzhou Xu, Yihang Chen, Xiaochong Jiang, Lifei Liu, Haoran Yu/Phantom Guardrails: When Self-Improving Agent Harnesses Fix Failures That Never HappenedUnknown

Self-improving AI agents are designed to learn from their mistakes. We show they can also hallucinate mistakes that never happened. We study this failure mode in automated harness optimization, where an LLM-based proposer edits an agent's scaffold, including prompts, parsers, filters, validators and guardrails, to eliminate observed failures. But this process rarely asks first: was there a real failure to fix? We introduce the Counterfactual Fabrication Lab, a deterministic micro-lab where the correct action is known: do nothing. The lab plants a candidate guardrail for a failure class that provably never occurs, presents only legal episodes, and uses a byte-exact oracle to check every cited violation. The proposer behaves as expected on real violations and abstains on featureless legal input. Yet when the legal input contains a harmless pattern resembling a familiar game rule, it invents a failure: in 15/60 runs, versus 0/60 on featureless input, it enables the nonexistent-rule guardrail and cites a violation the oracle refutes. The effect is structured, not indiscriminate. In single-shot proposals it appears only when three conditions coincide: a rule-shaped pattern, an open-ended rule set and an instruction that presupposes failures. Removing any of these conditions eliminates the fabrication. Because the invented guardrail changes no true outcome and cannot improve an already-perfect suppression score, the phenomenon is neither reward hacking nor over-refusal. It is a phantom guardrail: a fix for a failure that never happened, invisible to suppression-only acceptance. Inside an add-only accept loop it re-enters even without the failure-presupposing instruction, the loop's keep-adding role supplying the demand the instruction supplied in single shot, and once in it stays. We present the Counterfactual Fabrication Lab for measuring fabricated failures in self-improving agent harnesses.

agent app

Stars0

Forks0

HF Downloads—30d

Last commit—

Refreshed23d ago

Project healthUnknownNo activity data.

Production readinessResearch / EarlyBest for exploration and prototyping.

Risk notesUnknown licenseVerify license before production use.

AgentHub Score

55 / 100

Composite score from 6 signals. How we score →

Active project

55Score

Growth

40C

Activity

30C

Documentation

70C+

Maturity

45C

Community

42C

Production

58C

GitHub stars · 31 days observed0 not enough history

snapshots

Repository activity · 31 days observedReal snapshots from pushed_at

inactivepushed

2026-07-262026-08-27

Practical assessment

Should you use it?

✓ Best for

Research and experimentation
Prototype development
Learning agentic patterns

◎ Strengths

Active community
Open source
Well-documented API

✕ Not ideal for

Untested at scale without validation
Teams without AI/ML expertise

⚠ Watch-outs

Review changelog before updating
Verify license for commercial use

Technical details

What's inside

Language—

License—

Sourcearxiv

Open source✗ No

Commercial use—

Docs—

Demo—

PaperarXiv ↗

AgentHub Score

Score 55/100

Below average

Alternatives

OccuReward: LLM-Guided Occupant-Centric Reward Shaping for Demographic Equity in Grid-Interactive Buildings

0 · agent app

Unaccountable Delegation, Fading Skills: Mapping the Risks of Workplace AI Agents

0 · agent app

Discovering Adaptive Transmission Programs for Collective Innovation

0 · agent app

Agentic AI-driven Immersive Simulation: A Knowledge-Aware Virtual Training Platform forHigh Dose Rate (HDR) Brachytherapy

0 · agent app

55 Compare all →

Recent activity

Latest commit ——

Indexed by AgentHub crawler23d ago

Monitor for new releasesongoing