Self-Reflective APIs: Structure Beats Verbosity for AI Agent Recovery
On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks
Abstract (arXiv)
When an AI agent calls an API and hits a validation error, it needs more than what went wrong -- it needs what to do next. A self-reflective API returns, on validation failure, a machine-readable recoveryfeedback.suggestions[] payload sufficient for the agent to repair the request and retry without external reasoning. On a leak-audited pilot (N=30 per cell, 3 LLMs, 10 adversarial tasks), structured suggestions lift task-completion rate by +36.7--40.0pp over plain-English diagnoses on Anthropic models (Fisher's exact p ≤ 0.0022), at 1.8--2.2× better per-success token efficiency. The lift is not significant on gpt-4o-mini (p=0.435); a second-domain replication on a billing API confirms the pattern. The comparison only holds after auditing two undocumented classes of answer leakage in LLM benchmarks. We shipauditpromptleakage.py as reusable CI infrastructure. Code and data: https://github.com/arquicanedo/self-reflective-apis.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 6 of its 17 references that are in the map. First posted on arXiv 3 Jun 2026.
Builds on
6 of 17 references.
References · 6
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
- 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
- 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
- 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Structured Feedback Improves Repair in an LLM Agent Loop
- 2026RAIL Guard: Closing the Evaluation-to-Remediation Gap in Responsible AI for LLM Agents
- 2026Self-Designed Evaluators and Warm Memory for Long-Horizon Agents
- 2026Closing the Reflection Gap: A Free Calibration Bonus for Agentic RL
- 2026From Confident Closing to Silent Failure: Characterizing False Success in LLM Agents
- 2026Automated Benchmark Auditing for AI Agents and Large Language Models
- 2026Deterministic Replay for AI Agent Systems
- 2025Reflection-Driven Control for Trustworthy Code Agents