SciAgentArena is a new interactive benchmark for AI agents on scientific tasks that finds agents handle clear data-analysis workflows but struggle with novel insights, self-directed exploration, and open-ended questions.
hub Canonical reference
Agentic ai for scientific discovery: A survey of progress, challenges, and future directions
Canonical reference. 100% of citing Pith papers cite this work as background.
18
Pith papers citing it
13
external citations · external index
Background
100% of classified citations
hub tools
citation-role summary
background 6
citation-polarity summary
roles
background 6polarities
background 6representative citing papers
GenCellAgent deploys a planner-executor-evaluator LLM agent loop to automatically select, adapt, and refine segmentation tools for diverse cellular microscopy images, matching or exceeding specialist performance on 4,718 images across seven benchmarks while handling out-of-distribution and novel-ves
PseudoBench shows current LLM agents produce persuasive pseudoscientific reports with near-zero refusal rates and at most 27.4% resistance.
LLMs given only research questions from 1000 arXiv CS papers recommend a narrower set of methods than the original papers, with effective model-entity diversity dropping from 1232 to 59-96 and stronger agreement among LLMs than with papers.
Decentralized AI agent teams self-organize around hypotheses, critique proposals, and share knowledge to outperform single-agent baselines on biomedical ML, language-model optimization, and protein fitness tasks.
A multi-agent AI framework using processing and acoustic agents achieves 91.6% accuracy and 0.821 F1 score for in-situ porosity defect detection in wire-arc additive manufacturing.
Small LMs reach 77.1% accuracy at comparative forecasting of research idea success on benchmarks after supervised fine-tuning, with RLVR yielding interpretable reasoning at 71.35%.
The 2025 AI Agent Index catalogs technical and safety details for 30 deployed AI agents and finds low developer transparency on safety, evaluations, and societal impacts.
NEXUS is a code-centric multi-agent framework with hierarchical verification that autonomously constructs and refines neuroimaging workflows, outperforming static baselines on ADHD-200 and ADNI data.
AblateCell reproduces baselines in three single-cell perturbation repositories with 88.9% success and recovers ground-truth critical components with 93.3% accuracy via closed-loop ablation.
CARIS is a new agentic LLM framework that automates clinical research workflows from planning to reporting in a coding-free and privacy-preserving manner, achieving high completeness scores on heterogeneous datasets.
The paper introduces an agentic AI platform to train and support recovered soldiers as peer facilitators providing mental health triage and interventions in austere battlefield environments.
Proposes foundation models and decision-theoretic policies to manage evolving source representations and optimize follow-up resource allocation in LSST-scale time-domain astronomy.
A validation-gated multi-agent framework enables online adaptation of thermal-hydraulic surrogates and reduces forecast error by 19% under regime shifts on experimental loop data.
A survey organizing AI-powered research automation into five workflow stages, defining AutoResearch and Vibe Research, and proposing five evaluation dimensions while noting domain-conditioned limits on autonomy.
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.
URSA is a modular agent ecosystem that uses LLMs and scientific tools to accelerate research tasks of varying complexity.
A survey consolidating benchmarks, agent frameworks, real-world applications, and protocols for LLM-based autonomous agents into a proposed taxonomy with recommendations for future research.
citing papers explorer
-
Benchmarking AI Agents for Addressing Scientific Challenges Across Scales
SciAgentArena is a new interactive benchmark for AI agents on scientific tasks that finds agents handle clear data-analysis workflows but struggle with novel insights, self-directed exploration, and open-ended questions.
-
GenCellAgent: Generalizable, Training-Free Cellular Image Segmentation via Large Language Model Agents
GenCellAgent deploys a planner-executor-evaluator LLM agent loop to automatically select, adapt, and refine segmentation tools for diverse cellular microscopy images, matching or exceeding specialist performance on 4,718 images across seven benchmarks while handling out-of-distribution and novel-ves
-
PseudoBench: Measuring How Agentic Auto-Research Fuels Pseudoscience
PseudoBench shows current LLM agents produce persuasive pseudoscientific reports with near-zero refusal rates and at most 27.4% resistance.
-
Thinking Like a Scientist? A Structural Study of LLM-Generated Research Methods
LLMs given only research questions from 1000 arXiv CS papers recommend a narrower set of methods than the original papers, with effective model-entity diversity dropping from 1232 to 59-96 and stronger agreement among LLMs than with papers.
-
AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
Decentralized AI agent teams self-organize around hypotheses, critique proposals, and share knowledge to outperform single-agent baselines on biomedical ML, language-model optimization, and protein fitness tasks.
-
In-situ process monitoring for defect detection in wire-arc additive manufacturing: an agentic AI approach
A multi-agent AI framework using processing and acoustic agents achieves 91.6% accuracy and 0.821 F1 score for in-situ porosity defect detection in wire-arc additive manufacturing.
-
Teaching Language Models to Forecast Research Success Through Comparative Idea Evaluation
Small LMs reach 77.1% accuracy at comparative forecasting of research idea success on benchmarks after supervised fine-tuning, with RLVR yielding interpretable reasoning at 71.35%.
-
The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems
The 2025 AI Agent Index catalogs technical and safety details for 30 deployed AI agents and finds low developer transparency on safety, evaluations, and societal impacts.
-
Towards a Virtual Neuroscientist: Autonomous Neuroimaging Analysis via Multi-Agent Collaboration
NEXUS is a code-centric multi-agent framework with hierarchical verification that autonomously constructs and refines neuroimaging workflows, outperforming static baselines on ADHD-200 and ADNI data.
-
AblateCell: A Reproduce-then-Ablate Agent for Virtual Cell Repositories
AblateCell reproduces baselines in three single-cell perturbation repositories with 88.9% success and recovers ground-truth critical components with 93.3% accuracy via closed-loop ablation.
-
Coding-Free and Privacy-Preserving Agentic Framework for Data-Driven Clinical Research
CARIS is a new agentic LLM framework that automates clinical research workflows from planning to reporting in a coding-free and privacy-preserving manner, achieving high completeness scores on heterogeneous datasets.
-
Train the Trainers -- An Agentic AI Framework for Peer-Based Mental Health Support in Battlefield Environments
The paper introduces an agentic AI platform to train and support recovered soldiers as peer facilitators providing mental health triage and interventions in austere battlefield environments.
-
Toward decision-aware AI for LSST-scale time-domain astronomy
Proposes foundation models and decision-theoretic policies to manage evolving source representations and optimize follow-up resource allocation in LSST-scale time-domain astronomy.
-
Validation-Gated Multi-Agent Governance for Online Adaptation of Thermal-Hydraulic Surrogate Models under Operating-Regime Shift
A validation-gated multi-agent framework enables online adaptation of thermal-hydraulic surrogates and reduces forecast error by 19% under regime shifts on experimental loop data.
-
AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery
A survey organizing AI-powered research automation into five workflow stages, defining AutoResearch and Vibe Research, and proposing five evaluation dimensions while noting domain-conditioned limits on autonomy.
-
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.
-
URSA: The Universal Research and Scientific Agent
URSA is a modular agent ecosystem that uses LLMs and scientific tools to accelerate research tasks of varying complexity.
-
From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review
A survey consolidating benchmarks, agent frameworks, real-world applications, and protocols for LLM-based autonomous agents into a proposed taxonomy with recommendations for future research.