TACO is a self-evolving, plug-and-play compression framework that filters low-value terminal observations while preserving task-relevant signals, yielding 1-4% accuracy gains and better token efficiency on TerminalBench and related benchmarks.
_v2" or similar) Output a single JSON object with these fields: {
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression
TACO is a self-evolving, plug-and-play compression framework that filters low-value terminal observations while preserving task-relevant signals, yielding 1-4% accuracy gains and better token efficiency on TerminalBench and related benchmarks.