NQS-Agent introduces health-aware agentic hyperparameter optimization for neural-network quantum states, demonstrating improved results over human-tuned baselines on the square-lattice J1-J2 Heisenberg model by incorporating optimization trajectory stability.
hub Canonical reference
From ai for science to agentic science: A survey on autonomous scientific discovery
Canonical reference. 100% of citing Pith papers cite this work as background.
25
Pith papers citing it
4
external citations · external index
Background
100% of classified citations
hub tools
citation-role summary
background 7
citation-polarity summary
fields
cs.AI 10 cs.LG 4 cond-mat.mtrl-sci 2 cs.MA 2 cond-mat.str-el 1 cs.CL 1 cs.CY 1 cs.GR 1 cs.SE 1 physics.chem-ph 1years
2026 25roles
background 6polarities
background 6representative citing papers
PhySciBench benchmark shows current AI models achieve at most 33.5% accuracy on physical science tasks; DelveAgent framework improves accuracy by up to 7.5 points and cuts costs to one-third.
Battery-Sim-Agent reframes inverse battery parameter estimation as an LLM reasoning task in closed loop with a simulator and outperforms Bayesian optimization baselines on diverse benchmarks.
EIG represents research ideas as evolving graphs with nodes for claims and edges for relations, using a learned controller for edits and commits to produce higher-quality scientific proposals than text-only multi-agent baselines.
SkillFoundry mines heterogeneous scientific resources into a self-evolving library of validated agent skills, with 71.1% novelty versus prior libraries and measurable gains on coding benchmarks plus two genomics tasks.
SASAV introduces the first fully autonomous multi-agent system for scientific data analysis and visualization that operates without external prompting or human-in-the-loop feedback.
El Agente Quntur is a new multi-agent system that uses reasoning over literature and software documentation to autonomously handle the full workflow of quantum chemistry experiments in ORCA.
AdsMind is a multi-agent LLM framework with MLFF relaxation feedback that achieves 100% and 98.8% success on AA20 and OCD-GMAE62 benchmarks using roughly 4 relaxations per case and avoids sign errors seen in open-loop baselines on DFT checks.
PseudoBench shows current LLM agents produce persuasive pseudoscientific reports with near-zero refusal rates and at most 27.4% resistance.
AgentCo-op retrieves and assembles existing agents and tools into interoperable workflows for open-world scientific tasks, showing effectiveness in genomics case studies and competitive benchmark results with lower costs.
DrugSAGE accumulates cross-task memory of skills, statistical evidence, and recurring errors to let LLM agents achieve top-ranked performance on molecular property prediction tasks with reduced or zero test-time search.
Malicious actors could use AI agents to submit large numbers of fake papers, inflating the submission count and thereby raising the acceptance odds for a small set of chosen legitimate papers under stable conference acceptance rates.
LLMs exhibit Bayesian-like hypothesis updating with strong-sampling bias and an evaluation-generation gap but generalize poorly outside observed data.
An agentic framework fusing large atomic and language models rediscovers 66 known superconductors and guides experimental verification of four new ones with transition temperatures from 2.5 K to 6.5 K.
A four-phase multi-agent co-scientist tests natural-language hypotheses on cardiac and glioma MRI and labels outcomes Supported, Refuted, Underpowered, or Invalid with an executable evidence trail.
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.
QUASAR is a new autonomous LLM-based system that orchestrates multi-scale atomistic simulations and benchmarks as a general reasoning tool rather than a narrow automation script.
A perspective article defining world models as finite-resource compression of physical state transitions and outlining a roadmap toward physical AGI via unified representations and interactive simulators.
Introduces consensus objective aggregation for meta-optimization of scientific discovery and reports improved scaling and speedup for 3-SAT algorithm discovery using digital MemComputing machines.
HACO adapts MaskGIT from vision into MaskGXT with symmetry tokens and stratified sampling, reaching 79.06% METRe accuracy on MP-20 polymorph split versus 70.87% for the best baseline.
Survey of auto-research systems identifies objective, validation, and acceptance collapses, concluding that workflow closure does not equal scientific closure and advocating non-autonomous epistemic control.
Eywa enables language-based agentic AI systems to collaborate with specialized scientific foundation models for improved performance on structured data tasks.
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.
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.
citing papers explorer
-
NQS-Agent: Health-Aware Agentic Hyperparameter Optimization for Neural-Network Quantum States
NQS-Agent introduces health-aware agentic hyperparameter optimization for neural-network quantum states, demonstrating improved results over human-tuned baselines on the square-lattice J1-J2 Heisenberg model by incorporating optimization trajectory stability.
-
Deep Research in Physical Sciences: A Multi-Agent Framework and Comprehensive Benchmark
PhySciBench benchmark shows current AI models achieve at most 33.5% accuracy on physical science tasks; DelveAgent framework improves accuracy by up to 7.5 points and cuts costs to one-third.
-
Battery-Sim-Agent: Leveraging LLM-Agent for Inverse Battery Parameter Estimation
Battery-Sim-Agent reframes inverse battery parameter estimation as an LLM reasoning task in closed loop with a simulator and outperforms Bayesian optimization baselines on diverse benchmarks.
-
Evolving Idea Graphs with Learnable Edits-and-Commits for Multi-Agent Scientific Ideation
EIG represents research ideas as evolving graphs with nodes for claims and edges for relations, using a learned controller for edits and commits to produce higher-quality scientific proposals than text-only multi-agent baselines.
-
SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources
SkillFoundry mines heterogeneous scientific resources into a self-evolving library of validated agent skills, with 71.1% novelty versus prior libraries and measurable gains on coding benchmarks plus two genomics tasks.
-
SASAV: Self-Directed Agent for Scientific Analysis and Visualization
SASAV introduces the first fully autonomous multi-agent system for scientific data analysis and visualization that operates without external prompting or human-in-the-loop feedback.
-
El Agente Quntur: A research collaborator agent for quantum chemistry
El Agente Quntur is a new multi-agent system that uses reasoning over literature and software documentation to autonomously handle the full workflow of quantum chemistry experiments in ORCA.
-
AdsMind: A Physics-Grounded Multi-Agent System for Self-Correcting Discovery of Adsorption Configurations on Heterogeneous Catalyst Surfaces
AdsMind is a multi-agent LLM framework with MLFF relaxation feedback that achieves 100% and 98.8% success on AA20 and OCD-GMAE62 benchmarks using roughly 4 relaxations per case and avoids sign errors seen in open-loop baselines on DFT checks.
-
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.
-
AgentCo-op: Retrieval-Based Synthesis of Interoperable Multi-Agent Workflows
AgentCo-op retrieves and assembles existing agents and tools into interoperable workflows for open-world scientific tasks, showing effectiveness in genomics case studies and competitive benchmark results with lower costs.
-
DrugSAGE:Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery
DrugSAGE accumulates cross-task memory of skills, statistical evidence, and recurring errors to let LLM agents achieve top-ranked performance on molecular property prediction tasks with reduced or zero test-time search.
-
Position: Academic Conferences are Potentially Facing Denominator Gaming Caused by Fully Automated Scientific Agents
Malicious actors could use AI agents to submit large numbers of fake papers, inflating the submission count and thereby raising the acceptance odds for a small set of chosen legitimate papers under stable conference acceptance rates.
-
Hypothesis generation and updating in large language models
LLMs exhibit Bayesian-like hypothesis updating with strong-sampling bias and an evaluation-generation gap but generalize poorly outside observed data.
-
Agentic Fusion of Large Atomic and Language Models to Accelerate Superconductor Discovery
An agentic framework fusing large atomic and language models rediscovers 66 known superconductors and guides experimental verification of four new ones with transition temperatures from 2.5 K to 6.5 K.
-
VERITAS: A Multi-Agent Co-Scientist for Verifiable Image-Derived Hypothesis Testing
A four-phase multi-agent co-scientist tests natural-language hypotheses on cardiac and glioma MRI and labels outcomes Supported, Refuted, Underpowered, or Invalid with an executable evidence trail.
-
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.
-
QUASAR: A Universal Autonomous System for Atomistic Simulation and a Benchmark of Its Capabilities
QUASAR is a new autonomous LLM-based system that orchestrates multi-scale atomistic simulations and benchmarks as a general reasoning tool rather than a narrow automation script.
-
A Definition and Roadmap for World Models
A perspective article defining world models as finite-resource compression of physical state transitions and outlining a roadmap toward physical AGI via unified representations and interactive simulators.
-
Scientific discovery as meta-optimization: a combinatorial optimization case study
Introduces consensus objective aggregation for meta-optimization of scientific discovery and reports improved scaling and speedup for 3-SAT algorithm discovery using digital MemComputing machines.
-
Discovering Crystal Structure Prediction Algorithms with an AI Co-Scientist
HACO adapts MaskGIT from vision into MaskGXT with symmetry tokens and stratified sampling, reaching 79.06% METRe accuracy on MP-20 polymorph split versus 70.87% for the best baseline.
-
Workflow Closure Is Not Scientific Closure in Auto-Research Systems
Survey of auto-research systems identifies objective, validation, and acceptance collapses, concluding that workflow closure does not equal scientific closure and advocating non-autonomous epistemic control.
-
Heterogeneous Scientific Foundation Model Collaboration
Eywa enables language-based agentic AI systems to collaborate with specialized scientific foundation models for improved performance on structured data tasks.
-
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.
-
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.
-
SciHorizon-DataEVA: An Agentic System for AI-Readiness Evaluation of Heterogeneous Scientific Data
SciHorizon-DataEVA is a multi-agent system that applies Sci-TQA2 principles across four dimensions to assess AI-readiness of heterogeneous scientific data via dynamic profiling and self-correcting evaluation workflows.