Recurrent context compression can destabilize long-horizon agents, and a boundary-local verifier that tunes the compression prompt through paired rollouts improves reliability on AppWorld.
So do not write code making calls to os-level modules and functions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability
Recurrent context compression can destabilize long-horizon agents, and a boundary-local verifier that tunes the compression prompt through paired rollouts improves reliability on AppWorld.