Reflex: Fast Robot Policy Serving by Reusing and Correcting Past Actions
Overview
This research presents Reflex, a new serving layer for robot policies that addresses latency and throughput bottlenecks by caching complete action chunks rather than intermediate computations. The method employs a two-level correction mechanism to handle observation-action mismatches and accumulated errors without modifying the underlying policy. Evaluated on representative workloads and real robots, Reflex improves inference latency by 1.4x to 11x and throughput by 2.0x to 2.2x while preserving comparable task success rates.
Generated from attributed reports · Updated 1 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · inference latency improvement: 1.4 other · Basis not reported · Differing source assertions
“isions, assembles compatible chunks, and applies lightweight residual correction to limit action mismatch. At the execution level, it captures task progress and adaptively refreshes the original policy to limit accumulated errors and balance inference cost. Without modifying the underlying policy, Reflex improves inference latency by 1.4x to 11x and throughput by 2.0x to 2.2x on representative workloads and real robo”
Exact source · revision 1Source owner not reported
Reported quantity · inference latency improvement: 11 other · Basis not reported · Differing source assertions
“isions, assembles compatible chunks, and applies lightweight residual correction to limit action mismatch. At the execution level, it captures task progress and adaptively refreshes the original policy to limit accumulated errors and balance inference cost. Without modifying the underlying policy, Reflex improves inference latency by 1.4x to 11x and throughput by 2.0x to 2.2x on representative workloads and real robo”
Exact source · revision 1Source owner not reported
Reported quantity · throughput improvement: 2 other · Basis not reported · Differing source assertions
“isions, assembles compatible chunks, and applies lightweight residual correction to limit action mismatch. At the execution level, it captures task progress and adaptively refreshes the original policy to limit accumulated errors and balance inference cost. Without modifying the underlying policy, Reflex improves inference latency by 1.4x to 11x and throughput by 2.0x to 2.2x on representative workloads and real robo”
Exact source · revision 1Source owner not reported
Reported quantity · throughput improvement: 2.2 other · Basis not reported · Differing source assertions
“isions, assembles compatible chunks, and applies lightweight residual correction to limit action mismatch. At the execution level, it captures task progress and adaptively refreshes the original policy to limit accumulated errors and balance inference cost. Without modifying the underlying policy, Reflex improves inference latency by 1.4x to 11x and throughput by 2.0x to 2.2x on representative workloads and real robo”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalReflex: Fast Robot Policy Serving by Reusing and Correcting Past Actions
This research presents Reflex, a new serving layer for robot policies that addresses latency and throughput bottlenecks by caching complete action chunks rather than intermediate computations. The method employs a two-level correction mechanism to handle observation-action mismatches and accumulated errors without modifying the underlying policy. Evaluated on representative workloads and real robots, Reflex improves inference latency by 1.4x to 11x and throughput by 2.0x to 2.2x while preserving comparable task success rates.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).