paper: Poka-Yoke for AI Agents (NeurIPS draft) #596

Merged
perplexity merged 4 commits from paper/poka-yoke-for-agents into main 2026-04-13 01:01:52 +00:00

4 Commits

Author SHA1 Message Date
dea37bf6e5 Merge branch 'main' into paper/poka-yoke-for-agents
Some checks failed
Smoke Test / smoke (pull_request) Failing after 5s
2026-04-13 01:01:40 +00:00
0ec08b601e Merge pull request 'fix: Poka-Yoke paper review fixes (path injection, guardrail 5, broader impact)' (#598) from fix/poka-yoke-review-fixes into paper/poka-yoke-for-agents
Some checks failed
Smoke Test / smoke (pull_request) Failing after 6s
2026-04-13 00:59:06 +00:00
93db917848 fix: Path injection vulnerability, complete guardrail 5, add broader impact section
Some checks failed
Smoke Test / smoke (pull_request) Failing after 7s
- Guardrail 4: Replace str.startswith() with Path.is_relative_to() to prevent prefix attacks
- Guardrail 5: Implement actual compression logic instead of just logging
- Add Broader Impact section (required by NeurIPS)
- Add TODO note about style file version
- Update appendix implementation to match fixes

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-13 00:13:38 +00:00
Alexander Whitestone
7efe9877e1 paper: Poka-Yoke for AI Agents (NeurIPS draft)
Some checks failed
Smoke Test / smoke (pull_request) Failing after 8s
Five lightweight guardrails for LLM agent systems:
1. JSON repair for tool arguments (1400+ failures eliminated)
2. Tool hallucination detection
3. Return type validation
4. Path injection prevention
5. Context overflow prevention

44 lines of code, 455us overhead, zero quality degradation.
Draft: main.tex (NeurIPS format) + references.bib
2026-04-12 19:09:59 -04:00