llm-kb
← Back to research
Benchmark

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.

0 engagement·1 source·Fri, Jul 10, 2026, 12:04 PM
LongMedBench is constructed via a reproducible pipeline integrating MIMIC-IV admission records and clinical notes into time-series events. It focuses on longitudinal clinical reasoning, where agents must synthesize information across multiple encounters. The benchmark aims to push evaluation beyond short-context knowledge QA and tool use, reflecting the real-world nature of medical care.

Entities

LongMedBench(benchmark)MIMIC-IV(tool)

Related

BenchmarkFri, Jul 10, 2026, 06:52 AM

MedRealMM: A Real-World Multimodal Benchmark for Chinese Online Medical Consultation

Researchers introduce MedRealMM, a large-scale benchmark for multimodal online medical consultation built from de-identified patient-doctor interactions from a nationwide Chinese internet hospital. It addresses limitations of existing benchmarks that rely on synthetic data or omit patient-uploaded images. The benchmark aims to better align LLM evaluation with real clinical practice.

0 engagement·1 source·arxiv
arXiv
BenchmarkThu, Jul 9, 2026, 09:56 PM

Long-Horizon-Terminal-Bench: New Benchmark Tests AI Agents on Long-Horizon Tasks with Dense Rewards

Researchers introduced Long-Horizon-Terminal-Bench, a benchmark of 46 long-horizon tasks across nine categories, including experiment reproduction and software engineering. Unlike existing benchmarks that evaluate only final outcomes, it uses dense reward signals to measure intermediate progress, providing a more complete picture of agent capability.

0 engagement·1 source·arxiv
arXiv
BenchmarkTue, Jul 7, 2026, 04:43 PM

DataGovBench: New benchmark evaluates LLMs on real-world data analysis with large multi-tabular datasets

Researchers introduced DataGovBench, a benchmark derived from governmental open data to evaluate LLMs on practical data analysis tasks. It includes Table QA and Table Insight tasks, addressing limitations of existing benchmarks that focus on small tables and fact retrieval.

0 engagement·1 source·arxiv
arXiv
PaperTue, Jul 7, 2026, 04:12 PM

Question-type-specific LLM pipeline boosts BioASQ 14b biomedical QA

A new framework for BioASQ 14b Task B selects different inference procedures for yes/no, factoid, and list questions, improving answer robustness and evidence grounding. The approach uses question-type-specific prompting strategies rather than a single method for all queries.

0 engagement·1 source·arxiv
arXiv
BenchmarkThu, Jul 9, 2026, 05:59 PM

UniClawBench benchmark proposed for evaluating proactive AI agents in real-world tasks

Researchers introduced UniClawBench, a universal benchmark for evaluating proactive agents that operate everyday tools in real-world environments. Unlike existing benchmarks that rely on sandboxed settings and single-turn evaluations, UniClawBench aims to isolate specific model capabilities to identify root causes of agent failures.

0 engagement·1 source·arxiv
arXiv