Learn Before
Epistemic, Procedural-Memory, and Compliance Gaps - Engineering State-Bound Execution Runtimes for Autonomous Agents @ University of Michigan - Ann Arbor
Harness Scaling Foundations and Control Design Space - Long-Horizon Agent Reliability: Stateful Scaffolding and Runtime Verification @ University of Michigan - Ann Arbor
Operational Gaps in Long-Horizon Agent Execution - Long-Horizon Agent Reliability: Stateful Scaffolding and Runtime Verification @ University of Michigan - Ann Arbor
Failure-Driven Harness Optimization and Procedural Memory - Long-Horizon Agent Reliability: Stateful Scaffolding and Runtime Verification @ University of Michigan - Ann Arbor
Procedural-Memory Gap in Autonomous Agents
A procedural-memory gap is a longitudinal failure mode occurring across independent task executions where an agent correctly diagnoses an operational failure in an earlier run but neither retains nor invokes the resulting lesson when the same risk recurs. It contrasts with an epistemic gap (where necessary knowledge or methods are unavailable at decision time) and a procedural-compliance gap (where the correct procedure is active but remains incomplete or not followed).
0
1
Tags
Prep Sessions
Engineering State-Bound Execution Runtimes for Autonomous Agents @ University of Michigan - Ann Arbor
Ch.1 Operational Challenges and Systemic Bottlenecks - Engineering State-Bound Execution Runtimes for Autonomous Agents @ University of Michigan - Ann Arbor
Epistemic, Procedural-Memory, and Compliance Gaps - Engineering State-Bound Execution Runtimes for Autonomous Agents @ University of Michigan - Ann Arbor
Long-Horizon Agent Reliability: Stateful Scaffolding and Runtime Verification @ University of Michigan - Ann Arbor
Ch.1 Foundations and Operational Challenges - Long-Horizon Agent Reliability: Stateful Scaffolding and Runtime Verification @ University of Michigan - Ann Arbor
Harness Scaling Foundations and Control Design Space - Long-Horizon Agent Reliability: Stateful Scaffolding and Runtime Verification @ University of Michigan - Ann Arbor
Operational Gaps in Long-Horizon Agent Execution - Long-Horizon Agent Reliability: Stateful Scaffolding and Runtime Verification @ University of Michigan - Ann Arbor
Ch.3 State Persistence and Continuous Optimization - Long-Horizon Agent Reliability: Stateful Scaffolding and Runtime Verification @ University of Michigan - Ann Arbor
Failure-Driven Harness Optimization and Procedural Memory - Long-Horizon Agent Reliability: Stateful Scaffolding and Runtime Verification @ University of Michigan - Ann Arbor
Related
Epistemic Gap in Autonomous Agents
Procedural-Memory Gap in Autonomous Agents
Procedural-Compliance Gap in Autonomous Agents
Harness Scaling
Control-Signal Dilution
Mutable-State Ambiguity
Three Empirical Tests of Harness Scaling
Control-Layer Design Space for Long-Horizon Agents
Harness Scaling
Control-Signal Dilution
Mutable-State Ambiguity
Procedural-Memory Gap in Autonomous Agents
Epistemic Gap in Autonomous Agent Execution
Procedural-Compliance Gap in Autonomous Agent Execution
Mapping Operational Gaps to Runtime Control Points
Procedural-Memory Gap in Autonomous Agents
Failure-Driven Harness Optimization
Golden Rules for Harness Profile Development
Control Drift in Multi-Task Harness Optimization
Sparse Routing in Shared Agent Runbooks
Multi-Task Harness Abstraction via Hyper-Agent
Procedural Practices in Agent Harnesses
Single-Task Harness Adaptation Loop
Selective Filtering in Harness Learning
Procedural-Memory Gap in Autonomous Agents
Learn After
An agent that has the correct procedure active during an execution but fails to complete or follow it is exhibiting a procedural-compliance gap rather than a procedural-memory gap.
Why is a procedural-memory gap classified specifically as a longitudinal failure mode in autonomous agents?
In an autonomous agent, a procedural-memory gap begins with an inability to correctly diagnose the operational failure during its initial occurrence.
How does the prior acquisition of knowledge differ between an epistemic gap and a procedural-memory gap when an autonomous agent encounters an operational risk?
Across separate task runs, an autonomous agent successfully identifies the cause of an operational issue during the first run. However, when the exact same risk appears in a subsequent run, the agent fails to retain or apply the lesson it previously established. What type of failure mode does this represent?
In the context of agent failure modes, how is an epistemic gap defined, and at what specific point does it manifest?