SWE-Bench-CL reorganizes SWE-Bench Verified into 8 time-ordered sequences of 273 total tasks to measure continual learning in coding agents, adding CL-specific metrics and a semantic memory agent design.
Curriculum learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SWE-Bench-CL: Continual Learning for Coding Agents
SWE-Bench-CL reorganizes SWE-Bench Verified into 8 time-ordered sequences of 273 total tasks to measure continual learning in coding agents, adding CL-specific metrics and a semantic memory agent design.