Frontier coding agents surpass published Nature-family SOTA on only 17.8% of 90 sealed scientific tasks, mostly by recasting problems as supervised ML rather than inventing methods.
hub
Evoscientist: Towards multi-agent evolving ai scientists for end-to-end scientific discovery
21 Pith papers cite this work. Polarity classification is still indexing.
21
Pith papers citing it
hub tools
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
A survey of 1,250 papers organizes AI self-improvement along two axes—what is improved and loop closure—finding that demonstrated self-improvement strength tracks a verification hierarchy from formal verifiers down to intrinsic self-assessment.
SAGE with MHFA improves failure recovery in autonomous research agents, raising metrics-bearing outputs from 42% to 92% on a 12-topic benchmark versus single-reflection baselines.
AHOIS is a Socratic multi-agent AI that autonomously discovers and validates a random-interference encoding strategy for multimode fiber optics, achieving 76.97% MNIST and 83.17% Fashion-MNIST accuracy with 16x16 measurements of effective rank 56.9.
Xcientist is a research harness that externalizes an AI scientist's literature grounding, idea evolution, experiments, and repairs into auditable artifacts, demonstrated on memory, traffic forecasting, and PDE-solving tasks.
PseudoBench shows current LLM agents produce persuasive pseudoscientific reports with near-zero refusal rates and at most 27.4% resistance.
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.
ScientistOne introduces Chain-of-Evidence and an audit system that achieves zero hallucinated references, perfect score verification, and top method-code alignment while matching or beating human experts on five frontier tasks and generalizing to six more.
A repository-level AGENTS.md governance framework with commit-level AI disclosure, session logging, pre-commit gates, and mandatory human review is demonstrated on two new TMAP8 validation cases.
NanoResearch introduces a tri-level co-evolving framework of skills, memory, and policy to personalize LLM-powered research automation across projects and users.
NeuroClaw is a domain-specialized multi-agent framework with NeuroBench benchmark that improves executability and reproducibility for multimodal neuroimaging research.
XtraGPT is a suite of 1.5B-14B parameter open-source LLMs fine-tuned on 140,000 revision pairs from 7,000 top-tier papers to support controllable, context-aware academic paper editing.
A 40-task, 10-domain benchmark finds current auto-research agents and LLMs score only ~20–26 on re-discovering real published scientific artifacts.
A multi-agent harness autonomously generates functional single-page VIS apps with linked views for scientific data tasks using coordinated skills for analysis, planning, implementation, and evaluation.
GEAR applies genetic algorithms to maintain and evolve multiple research states in autonomous code agents, outperforming single-path baselines by continuing to discover improvements over extended runs.
Subagent architectures deliver stable high-throughput optimization under tight time limits while agent teams enable deeper refactoring at the cost of higher fragility.
Survey framing LLM agents as model-plus-harness systems, decomposing harness responsibilities, mapping them to tasks, and highlighting open challenges in evaluation, safety, and co-evolution.
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.
AI can generate research artifacts faster than it can verify them, so across all eight lifecycle stages the credible deployment mode is human-governed collaboration rather than full autonomy.
ARIS is a three-layer open-source system that uses cross-model adversarial collaboration plus claim-auditing pipelines to make LLM-driven research workflows more reliable.
LARA-HPC introduces a validation-first agentic system with dry-run verification and multi-phase refinement that improves robustness of AI-generated DFT workflows on HPC systems.
citing papers explorer
-
NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?
Frontier coding agents surpass published Nature-family SOTA on only 17.8% of 90 sealed scientific tasks, mostly by recasting problems as supervised ML rather than inventing methods.
-
Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops
A survey of 1,250 papers organizes AI self-improvement along two axes—what is improved and loop closure—finding that demonstrated self-improvement strength tracks a verification hierarchy from formal verifiers down to intrinsic self-assessment.
-
One Reflection Is Not Enough: Self-Correcting Autonomous Research via Multi-Hypothesis Failure Attribution
SAGE with MHFA improves failure recovery in autonomous research agents, raising metrics-bearing outputs from 42% to 92% on a 12-topic benchmark versus single-reflection baselines.
-
Socratic agents for autonomous scientific discovery in high-dimensional physical systems
AHOIS is a Socratic multi-agent AI that autonomously discovers and validates a random-interference encoding strategy for multimode fiber optics, achieving 76.97% MNIST and 83.17% Fashion-MNIST accuracy with 16x16 measurements of effective rank 56.9.
-
Externalizing Research Synthesis and Validation in AI Scientists through a Research Harness
Xcientist is a research harness that externalizes an AI scientist's literature grounding, idea evolution, experiments, and repairs into auditable artifacts, demonstrated on memory, traffic forecasting, and PDE-solving tasks.
-
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.
-
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.
-
ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence
ScientistOne introduces Chain-of-Evidence and an audit system that achieves zero hallucinated references, perfect score verification, and top method-code alignment while matching or beating human experts on five frontier tasks and generalizing to six more.
-
Bridging the Gap on AI-Assisted Scientific Software Development Through Transparency and Traceability
A repository-level AGENTS.md governance framework with commit-level AI disclosure, session logging, pre-commit gates, and mandatory human review is demonstrated on two new TMAP8 validation cases.
-
NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation
NanoResearch introduces a tri-level co-evolving framework of skills, memory, and policy to personalize LLM-powered research automation across projects and users.
-
NeuroClaw Technical Report
NeuroClaw is a domain-specialized multi-agent framework with NeuroBench benchmark that improves executability and reproducibility for multimodal neuroimaging research.
-
XtraGPT: Context-Aware and Controllable Academic Paper Revision via Human-AI Collaboration
XtraGPT is a suite of 1.5B-14B parameter open-source LLMs fine-tuned on 140,000 revision pairs from 7,000 top-tier papers to support controllable, context-aware academic paper editing.
-
ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research
A 40-task, 10-domain benchmark finds current auto-research agents and LLMs score only ~20–26 on re-discovering real published scientific artifacts.
-
Toward AI VIS Co-Scientists: A General and End-to-End Agent Harness for Solving Complex Data Visualization Tasks
A multi-agent harness autonomously generates functional single-page VIS apps with linked views for scientific data tasks using coordinated skills for analysis, planning, implementation, and evaluation.
-
GEAR: Genetic AutoResearch for Agentic Code Evolution
GEAR applies genetic algorithms to maintain and evolve multiple research states in autonomous code agents, outperforming single-path baselines by continuing to discover improvements over extended runs.
-
An Empirical Study of Multi-Agent Collaboration for Automated Research
Subagent architectures deliver stable high-throughput optimization under tight time limits while agent teams enable deeper refactoring at the cost of higher fragility.
-
From Question Answering to Task Completion: A Survey on Agent System and Harness Design
Survey framing LLM agents as model-plus-harness systems, decomposing harness responsibilities, mapping them to tasks, and highlighting open challenges in evaluation, safety, and co-evolution.
-
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.
-
AI for Auto-Research: Roadmap & User Guide
AI can generate research artifacts faster than it can verify them, so across all eight lifecycle stages the credible deployment mode is human-governed collaboration rather than full autonomy.
-
ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration
ARIS is a three-layer open-source system that uses cross-model adversarial collaboration plus claim-auditing pipelines to make LLM-driven research workflows more reliable.
-
LARA: Validation-Driven Agentic Supercomputer Workflows for Atomistic Modeling
LARA-HPC introduces a validation-first agentic system with dry-run verification and multi-phase refinement that improves robustness of AI-generated DFT workflows on HPC systems.