# Behavioral Path Optimization

The work proposes GlitchPatch, an external framework that repairs glitch tokens without accessing model internals by optimizing input tokenization: offline, Behavioral Path Optimization (BPO) searches for the behaviorally optimal equivalent token sequence for each glitch token and compiles validated replacements into a rule table; online, only the IDs of matched glitch tokens in the canonical token sequence are substituted. Across ten models spanning six tokenizer families, it achieves an 85.10% mean fix rate, 14.37 percentage points above the strongest baseline, reduces the mean glitch rate from 14.88% to 2.27%, attains 0.00% regression in full-vocabulary evaluation, and keeps the mean online latency increase below 0.1%.

The work proposes GlitchPatch, an external framework that repairs glitch tokens without accessing model internals by optimizing input tokenization: offline, Behavioral Path Optimization (BPO) searches for the behaviorally optimal equivalent token sequence for each glitch token and compiles validated replacements into a rule table; online, only the IDs of matched glitch tokens in the canonical token sequence are substituted. Across ten models spanning six tokenizer families, it achieves an 85.10% mean fix rate, 14.37 percentage points above the strongest baseline, reduces the mean glitch rate from 14.88% to 2.27%, attains 0.00% regression in full-vocabulary evaluation, and keeps the mean online latency increase below 0.1%.