arXiv AI
Reading Right, Acting Wrong: Diagnosing Decision Failures of System One Models in Agent Loops
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Sep 17
Locating Hidden Failures Makes Long-Horizon Agents More Reliable
The paper introduces Traverse, a benchmark of 2,518 agent trajectories and 6,967 annotated mistakes across software engineering, computer use, and science tasks, revealing that failures often go unrecovered and can cause irreversible harm before a run is deemed successful. It shows that human judges struggle to detect the first mistake in most runs, while a 4‑billion‑parameter verifier called Scout can locate failures more effectively and improve task success when used to select among candidate runs. The study demonstrates that making failure detection inexpensive and reliable can enable long‑horizon agents to learn from their own mistakes and increase trustworthiness in autonomous AI.
arXiv AI
Aug 25
Robustness Analysis of Agentic AI to Inconsistent and Incomplete Tool Responses
arXiv:2608.22676v1 Announce Type: new Abstract: Robustness to a bad tool return means answering it in the way that return calls for, which depends on how the tool went wrong. A tool that has failed a...
arXiv AI
Aug 17
Wrong but Useful: Trajectory Value Beyond Answer Correctness in Multi-Agent Messages
arXiv:2608. 14375v1 Announce Type: new Abstract: Multi-agent reasoning systems often use agreement, confidence, or automated scores to decide which messages should shape a final answer.
arXiv AI
Sep 21
When Should a Failing Robot Ask? Initiating Corrective Human-Robot Dialogue from Audited Sensor Evidence
arXiv:2609.21942v1 Announce Type: cross Abstract: A robot that fails at a task faces the first decision in corrective dialogue: act on its own diagnosis, consult another onboard sensor, or interrupt...
arXiv AI
Jun 2
FALAT: Tracing Failures in LLM Agent Trajectories via Dependency-Guided Search
arXiv:2606. 00765v1 Announce Type: new Abstract: LLM-based agents increasingly solve complex tasks through long trajectories involving reasoning steps, tool calls, and inter-agent communication.
arXiv AI
Sep 2
trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories
The paper "trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories" examines the limitations of outcome-only evaluation for large language model agents. Using a deterministic tool‑using support‑desk environment with a scripted oracle policy and a fault injector, the authors compare five different judging approaches—programmatic rules, outcome‑only, step‑rubric at two model sizes, and a self‑consistency ensemble—on metrics such as detection, step localisation, fault typing, calibration, and cost across 400 trajectories. The study finds that outcome‑only judges miss many silent faults and generate false positives, while step‑rubric judges achieve higher recall with no false alarms but at greater cost, and that none of the judges read the final reply, allowing fabricated promises to evade detection. "whyItMatters":"The findings highlight that current production‑default outcome‑only evaluations can overlook critical failures in agent behavior, underscoring the need for more nuanced, step‑level judging methods to ensure reliable LLM agent performance."