arXiv AI
Jul 17
Building Agent Harnesses for Scientific Curation from Multimodal Sources
arXiv:2606. 21005v2 Announce Type: replace Abstract: Scientific discovery workflows often depend on structured curation from the literature.
Sci-MMR: Benchmarking Multi-Step Evidence-Grounded Scientific Reasoning in Multimodal Agents
Sci‑MMR is a new benchmark for multi‑step evidence‑grounded scientific reasoning in multimodal agents, featuring 235 multi‑hop tasks across four disciplines and an average of nine figure panels per task. It evaluates not just final answer accuracy but also the recovery of structured evidence from scientific claims, citations, visual data, and supporting regions. Experiments on eight state‑of‑the‑art models show a gap of over 20 points between answer accuracy and complete evidence recovery, highlighting significant challenges in evidence acquisition and integration.
Related stories
arXiv AI
Sep 12
Mr.LHDR: A Benchmark for Multimodal Real-World Long-Horizon Deep Research Agents
Mr.LHDR is a new benchmark designed to evaluate deep research agents on long‑horizon, multimodal tasks. It presents questions built from hidden Node‑Relation graphs that require an average of 12.1 intermediate conclusions and a mean dependency depth of 10.4 before arriving at a single verifiable answer. The benchmark tests both final answers and the correctness of intermediate conclusions, using metrics such as Overall Accuracy, Strict Accuracy, Checklist Score, and Dependency‑Aware Checklist Score.
arXiv AI
Jun 12
SciR: A Controllable Benchmark for Scientific Reasoning in LLMs
arXiv:2606. 13020v1 Announce Type: new Abstract: Three paradigmatic forms of inference recur across scientific reasoning: deduction, induction, and causal abduction.
arXiv AI
Jul 20
ToolSciVer: Multimodal Scientific Claim Verification with Visual Tool Augmented Reinforcement Learning
arXiv:2607. 16131v1 Announce Type: cross Abstract: Multimodal Scientific Claim Verification (MSCV) requires models to verify scientific claims using visually grounded evidence from papers, including figures, tables, charts, and textual context.
arXiv AI
Sep 18
BioPhys-Bridge: A Benchmark for Interdisciplinary Scientific Reasoning in Physics-Grounded Biological Research
BioPhys-Bridge is a newly released benchmark dataset designed to evaluate language models on evidence‑grounded scientific reasoning within biophysical literature. Each of its 500 cases includes evidence blocks, stable IDs, quantitative values, units, equations, assumptions, mechanisms, and next‑step decisions, covering six biological domains and nine physical model families. The dataset enforces strict quality gates and has already been evaluated against several models, with DeepSeek‑V4‑Flash achieving the highest evidence‑ID F1 score of 0.360.
arXiv AI
Aug 11
MMArch: Benchmarking Multimodal Reasoning Grounded in Architectural Evidence
arXiv:2608. 09281v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) perform strongly on engineering imagery, yet existing benchmarks mostly test drawing recognition, information extraction, or compliance checking, leaving open whether models can combine distributed visual evidence with engineering principles to reach a conclusion.
arXiv AI
Jul 2
Autonomous Scientific Discovery via Iterative Meta-Reflection
arXiv:2607. 01131v1 Announce Type: cross Abstract: Autonomous scientific discovery systems offer the potential to accelerate research by automating the process of hypothesis generation and validation.
arXiv AI
Aug 3
M3MAD-Bench: Multi-Dimensional Evaluation of Multi-Agent Debate Across Domains and Modalities
arXiv:2601. 02854v2 Announce Type: replace Abstract: As an agent-level reasoning and coordination paradigm, Multi-Agent Debate (MAD) orchestrates multiple agents through structured debate to improve answer quality and support complex reasoning.
arXiv Computer Vision
Oct 21
EvaOmni: An Evidence-Grounded Benchmark for Audio-Visual Reasoning
EvaOmni is a new evidence‑grounded benchmark for audio‑visual reasoning, comprising 392 videos and 1,027 human‑annotated question‑answer pairs that span 15 capabilities and three difficulty levels. The benchmark requires models to provide both an answer and the supporting audio‑visual evidence intervals, and introduces Coverage Grounded (C.G.) and Bottleneck Grounded (B.G.) scores to evaluate evidence identification and temporal localization. Across 24 Omni LLMs, Gemini3.7‑Flash achieved the highest overall accuracy, yet its B.G. scores reveal significant room for improvement in grounded reasoning.
arXiv AI
Aug 10
Science Edge Evaluation: SEE the Missing Step Toward Real Scientific Discovery
arXiv:2608. 06931v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly involved in scientific discovery, yet it remains unclear whether they can support complex real laboratory science.
arXiv AI
Sep 28
BioEVAL: A global, multi-institutional benchmark of large language and multimodal models for bioengineering
BioEVAL is a global, multi‑institutional benchmark that evaluates large language and multimodal models on experimental reasoning tasks in bioengineering. It comprises 608 items across 11 bioengineering subfields, including 359 vetted multiple‑choice questions, 218 literature synthesis tasks, and 10 multimodal image‑interpretation problems. The benchmark was used to assess models such as ChatGPT, Gemini, and Grok, revealing accuracies up to 90% on MCQs, a 0.72 similarity score on literature synthesis, and 80% accuracy on multimodal tasks, with notable variation across subfields.
arXiv AI
Sep 30
OmniVCBench: Benchmarking Evidence-Grounded Multimodal Reasoning Towards AI Virtual Cells
OmniVCBench is a figure‑centric, source‑traceable benchmark designed to evaluate the interpretation component of Artificial Intelligence Virtual Cells (AIVCs). It comprises 6,077 curated question–answer pairs drawn from scientific figures and experimental contexts, organized into three scientific reasoning tasks that mirror the AIVC Predict–Explain–Discover agenda. The benchmark also introduces AIVC‑Judge, a task‑conditioned MLLM‑as‑a‑judge framework with reference‑aware rubrics, and a Model‑Derived Hard‑Negative Mining strategy to generate multiple‑choice distractors for efficient evaluation.