SAGEAgent: A Self-Evolving Agent for Cost-Aware Modality Acquisition in Multimodal Survival Prediction
Researchers propose SAGEAgent, a self-evolving agent that sequentially decides which diagnostic modalities to acquire for cancer survival prediction, balancing accuracy and cost. It follows the clinically mandated order of escalating burden, from demographics to genomic profiling. The agent actively reasons whether acquiring the next modality is justified for each patient, unlike current methods that assume all modalities are available or passively handle missing data.
Entities
Related
LongMedBench: New Benchmark Tests Medical Agents on Long-Horizon Clinical Decisions
Researchers introduced LongMedBench, a benchmark using real EHR data from MIMIC-IV to evaluate LLM-based medical agents on long-horizon clinical decision-making. Unlike prior short-context QA benchmarks, LongMedBench requires agents to aggregate evidence across repeated visits, tests, and treatments over time. This addresses a key gap in realistic assessment of medical AI.
Agora paper proposes auction-based task allocation for LLM agents
A new arXiv paper introduces Agora, a framework that uses an incentive-compatible auction mechanism to dynamically allocate tasks to expert LLMs and tools, aiming to improve reasoning performance while accounting for cost and performance variability. The approach addresses limitations in current orchestration methods that rely on coarse-grained function matching.
GATS framework eliminates LLM calls during agent planning inference
Researchers propose GATS (Graph-Augmented Tree Search), a planning framework that uses a layered world model and UCB1-based tree search to avoid LLM inference during planning, reducing computational cost and stochasticity. The approach outperforms LATS and ReAct on multi-step planning tasks.