PACE builds proxy benchmarks from non-agentic instances via relevance and global selection plus regression to predict agentic scores with MAE under 4%, Spearman correlation above 0.80, and 85% ranking accuracy at under 1% cost.
Transactions on Machine Learning Research , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Introduces Active Task Driving Memory (ATMem) and STR-GRPO to move GUI agents from passive record storage to actively maintained task states, tested on a new mobile benchmark with progress and scope-aware metrics.
ReFlect is a harness that wraps LLMs to detect and recover from reasoning errors, achieving 7-29 pp gains over direct CoT on long-horizon tasks and improving code patch quality to 82-87%.
A small set of sparse autoencoder features in LLMs drives shifts between generous and selfish allocations in dictator games, with causal patching and steering confirming their role and generalization to other social games.
citing papers explorer
-
What Memory Do GUI Agents Really Need? From Passive Records to Active Task-Driving States
Introduces Active Task Driving Memory (ATMem) and STR-GRPO to move GUI agents from passive record storage to actively maintained task states, tested on a new mobile benchmark with progress and scope-aware metrics.