# Accurate Failure Prediction in Agents Does Not Imply Effective Failure Prevention

arXiv: https://arxiv.org/abs/2602.03338 · HTML: https://mlsanity.com/paper/2602.03338/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 19 of its 23 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 19 of 19)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning](https://mlsanity.com/paper/2410.08146/) (2024)
- [Scalable Best-of-N Selection for Large Language Models via Self-Certainty](https://mlsanity.com/paper/2502.18581/) (2025)
- [Large Language Models Can Self-Correct with Key Condition Verification](https://mlsanity.com/paper/2405.14092/) (2024)
- [Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning](https://mlsanity.com/paper/2505.24726/) (2025)
- [Automating Steering for Safe Multimodal Large Language Models](https://mlsanity.com/paper/2507.13255/) (2025)
- [Capability Ceilings in Autoregressive Language Models: Empirical Evidence from Knowledge-Intensive Tasks](https://mlsanity.com/paper/2510.21866/) (2025)

## Built on by (most cited first, 15 of 15)

- [AEGIS: A Backup Reflex for Physical AI](https://mlsanity.com/paper/2606.06660/) (2026)
- [Looking Is Not Picking: An Attention-Segment Account of Tool-Selection Failures in LLM Agents](https://mlsanity.com/paper/2606.16364/) (2026)
- [Preventing Premature Commitment in Coding Agents with an Evidence-Conditioned Execution Layer](https://mlsanity.com/paper/2607.28815/) (2026)
- [Calibration Is Not Control: Why LLM-Agent Oversight Needs Intervention](https://mlsanity.com/paper/2606.21399/) (2026)
- [Don't Solve, Just Compare: Tiny Advisors for Runtime Intervention in LLM Agents](https://mlsanity.com/paper/2608.21027/) (2026)
- [Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluation](https://mlsanity.com/paper/2609.03727/) (2026)
- [ARBITER: Reasoning Trajectory Basins and Majority Vote Failures in Test-Time Sampling](https://mlsanity.com/paper/2605.26172/) (2026)
- [What Does a Skill Actually Do? Estimands and Evaluation Validity for Tool and Skill Use in LLM Agents: A Critical Review](https://mlsanity.com/paper/2609.33153/) (2026)
- [Don't Start What You Can't Finish: A Counterfactual Audit of Support-State Triage in LLM Agents](https://mlsanity.com/paper/2604.16752/) (2026)
- [Opera: A Verbal Critic Framework for Long-horizon Coding Agents](https://mlsanity.com/paper/2609.33987/) (2026)
- [What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents](https://mlsanity.com/paper/2609.39989/) (2026)
- [From Probe Scores to Alarm Policies: Operational Validity of Activation Monitors for Language-Model Agents](https://mlsanity.com/paper/2610.04575/) (2026)
- [Disentangling Task Difficulty from Run-Level Failure in Agent Failure Prediction](https://mlsanity.com/paper/2610.05572/) (2026)
- [From Uncertainty to Action: Learning to Steer LLM Agents](https://mlsanity.com/paper/2610.09115/) (2026)
- [RESCUE: Is This Alarm Worth Acting On? Counterfactual Evaluation of VLA Runtime Monitors](https://mlsanity.com/paper/2610.13516/) (2026)

## Abstract (arXiv)

Proactive interventions by LLM critic models are often assumed to improve reliability, yet their effects at deployment time are poorly understood. We show that a binary LLM critic with strong offline accuracy (AUROC 0.94) can nevertheless cause severe performance degradation, inducing a 26 percentage point (pp) collapse on one model while affecting another by near zero pp. This variability demonstrates that LLM critic accuracy alone is insufficient to determine whether intervention is safe. We identify a disruption-recovery tradeoff: interventions may recover failing trajectories but also disrupt trajectories that would have succeeded. Based on this insight, we propose a pre-deployment test that uses a small pilot of 50 tasks to estimate whether intervention is likely to help or harm, without requiring full deployment. Across benchmarks, the test correctly anticipates outcomes: intervention degrades performance on high-success tasks (0 to -26 pp), while yielding a modest improvement on the high-failure ALFWorld benchmark (+2.8 pp, p=0.014). The primary value of our framework is therefore identifying when not to intervene, preventing severe regressions before deployment.