Tag
This paper introduces ExTS, a tree-search policy for budget-constrained agentic search in LLM agents that improves over standard baselines in tasks like prompt optimization and code generation with an average +5.5% gain.
This paper introduces EcoAgent-Bench, a 304-task benchmark for evaluating LLM agents' economic decision-making under explicit budgets and priced actions, testing four cost-related decisions across five task families.
This paper investigates the optimal placement of expensive 'oracle' correctors within a swarm of unreliable agents to achieve correct consensus, revealing a submodular property and a budget-correctness frontier that depends on the cost–strength curvature.
This paper investigates whether online skill and memory modules for web agents are worth their token cost under a fixed inference budget, finding that a budget-matched vanilla baseline often matches or outperforms augmented methods across three domains and models.
This paper studies a staged promotion protocol for micro-pretraining, using escalating budgets from minutes to hours to filter configurations. It finds that early screens are useful but unstable, and that a staged approach can retain a long-horizon reference while identifying alternatives that fail continuation thresholds.
This paper proposes a staged factorial screening workflow for budget-constrained micro-pretraining, demonstrating that short designed experiments can identify stable hyperparameter penalty directions and support a screen-then-refine strategy.