OpenRCA 2.0 is the first cross-system RCA benchmark with step-wise causal annotations, revealing that 11 frontier LLMs achieve 20.7% exact root-cause recovery and struggle with causal grounding (61.5% vs 76.0% ungrounded).
MIT press, 2000
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Agentic memory improves clean reasoning but worsens performance when spurious patterns are present in stored trajectories; CAMEL calibration reduces this reliance while preserving clean performance.
Presents a causal inference framework for autonomous robot decision-making on task execution timing and strategy using estimates of battery usage and human obstructions, evaluated via a new Gazebo simulator called PeopleFlow against a non-causal baseline in a warehouse setting.
citing papers explorer
-
OpenRCA 2.0: From Outcome Labels to Causal Process Supervision
OpenRCA 2.0 is the first cross-system RCA benchmark with step-wise causal annotations, revealing that 11 frontier LLMs achieve 20.7% exact root-cause recovery and struggle with causal grounding (61.5% vs 76.0% ungrounded).
-
The Trap of Trajectory: Towards Understanding and Mitigating Spurious Correlations in Agentic Memory
Agentic memory improves clean reasoning but worsens performance when spurious patterns are present in stored trajectories; CAMEL calibration reduces this reliance while preserving clean performance.
-
Causality-enhanced Decision-Making for Autonomous Mobile Robots in Dynamic Environments
Presents a causal inference framework for autonomous robot decision-making on task execution timing and strategy using estimates of battery usage and human obstructions, evaluated via a new Gazebo simulator called PeopleFlow against a non-causal baseline in a warehouse setting.