The authors study prospective memory, in which an agent stores an intention that should be executed when an external condition becomes true.
Agents can budget external checks without sacrificing task quality
BudgetPM learns when to query external state now and when to reserve limited observation capacity for later intentions.
Academic
Zhengkun Di · Bin Shi · Kai Sun · Yiming Xu · Bo Dong
Xi’an Jiaotong University
Research Digest··2 min read
Thread:Agent Harness Optimization
Di and colleagues formulate external-state checking for stored intentions as a resource-allocation problem under a hard episode budget.
Why this paper
From Xi’an Jiaotong University · Part of Agent Harness Optimization, now 90 papers
In one line
BudgetPM allocates limited external observations across stored agent intentions to maximize task quality under a hard budget.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§