An LLM seeds and slots a task-specific architecture search space that conventional NAS then explores, reaching SOTA on 11 of 17 diverse NAS benchmarks.
hub Canonical reference
Agentrxiv: Towards collaborative autonomous research
Canonical reference. 83% of citing Pith papers cite this work as background.
24
Pith papers citing it
Background
83% of classified citations
abstract
Progress in scientific discovery is rarely the result of a single "Eureka" moment, but is rather the product of hundreds of scientists incrementally working together toward a common goal. While existing agent workflows are capable of producing research autonomously, they do so in isolation, without the ability to continuously improve upon prior research results. To address these challenges, we introduce AgentRxiv-a framework that lets LLM agent laboratories upload and retrieve reports from a shared preprint server in order to collaborate, share insights, and iteratively build on each other's research. We task agent laboratories to develop new reasoning and prompting techniques and find that agents with access to their prior research achieve higher performance improvements compared to agents operating in isolation (11.4% relative improvement over baseline on MATH-500). We find that the best performing strategy generalizes to benchmarks in other domains (improving on average by 3.3%). Multiple agent laboratories sharing research through AgentRxiv are able to work together towards a common goal, progressing more rapidly than isolated laboratories, achieving higher overall accuracy (13.7% relative improvement over baseline on MATH-500). These findings suggest that autonomous agents may play a role in designing future AI systems alongside humans. We hope that AgentRxiv allows agents to collaborate toward research goals and enables researchers to accelerate discovery.
hub tools
citation-role summary
background 5
dataset 1
citation-polarity summary
representative citing papers
The paper proposes AICID as a new identifier system to make the provenance of AI-generated scholarly work transparent and machine-readable.
ENPIRE supplies four modules (Environment, Policy Improvement, Rollout, Evolution) that turn real-world robot training into an autonomous optimization loop driven by coding agents.
EinsteinArena is a platform for AI agents to collectively discover new mathematical results through open interaction, achieving 12 new state-of-the-art outcomes including raising the 11-dimensional kissing number lower bound from 593 to 604.
AI CFD Scientist autonomously discovers a Spalart-Allmaras runtime correction reducing lower-wall Cf RMSE by 7.89% on the periodic hill at Reh=5600 while using a vision-language gate to detect 14 of 16 silent failures missed by solver checks.
Knows uses a YAML sidecar specification to provide structured, agent-consumable representations of research papers, yielding large accuracy gains for small LLMs on comprehension tasks and rapid community adoption via a public hub.
Agentic-Ideation uses oracle-guided multi-agent synthesis to generate efficient training trajectories for scientific ideation agents, reporting 11.91% quality gains and over 10x sample efficiency versus workflow baselines.
LLMs match original qualitative conclusions in 80% of 180 studies and effect sizes in 24%, performing similarly to humans in a tested subset, positioning them as a screening tool rather than a full replacement.
Arbor combines a coordinator, executors, and a hypothesis tree to enable cumulative autonomous research, outperforming Codex and Claude Code by over 2.5x on six real tasks and reaching 86.36% Any Medal on MLE-Bench Lite.
Signal-Driven Observation decouples observation from action frequency in long-horizon web agents by invoking selective task-relevant DOM reads only on signals such as URL changes or action failures.
A client-server swarm framework lets arbitrary agent code run on detached machines while shared servers train it, and context-timeline merging cuts actor-update time by 6.25x on AppWorld.
ResearchArena shows that agent-generated papers fail top-tier acceptance standards primarily due to fabricated results, underpowered experiments, and plan-execution mismatches that vary sharply by agent.
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.
Time-sliced training and a Future Alignment Score make LLMs generate research proposals that better anticipate post-cutoff published directions, with reported gains and two implemented proposals.
An agentic system produces traceable review packages and an un-finetuned 196B model using it covers more major issues than Gemini-3.1-Pro on 134 ICLR 2025 submissions while winning most blind comparisons to human committees.
GenoMAS deploys six specialized LLM agents with guided planning to preprocess transcriptomic data and identify genes, reaching 89.13% composite similarity and 60.48% F1 on the GenoTEX benchmark while outperforming prior methods.
Clarus is a four-layer collaboration infrastructure with a project-agent-resource model that reformulates research as an open, traceable, multi-participant process.
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.
AiraXiv is a proposed AI-driven platform for open preprints that supports human and AI authors with interactive UI and MCP-based interactions, validated by serving as the submission system for ICAIS 2025.
pAI/MSc is a customizable multi-agent system that reduces human steering by orders of magnitude when turning a hypothesis into a literature-grounded, mathematically established, experimentally supported manuscript draft in ML theory.
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.
The paper proposes a four-role framework for LLMs in scientific innovation and reviews methods, benchmarks, and limitations across Assistant, Collaborator, Scientist, and Evaluator roles.
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
-
Agentic Neural Architecture Search
An LLM seeds and slots a task-specific architecture search space that conventional NAS then explores, reaching SOTA on 11 of 17 diverse NAS benchmarks.
-
AICID: Unique Identifiers for AI Scientists
The paper proposes AICID as a new identifier system to make the provenance of AI-generated scholarly work transparent and machine-readable.
-
ENPIRE: Agentic Robot Policy Self-Improvement in the Real World
ENPIRE supplies four modules (Environment, Policy Improvement, Rollout, Evolution) that turn real-world robot training into an autonomous optimization loop driven by coding agents.
-
Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries
EinsteinArena is a platform for AI agents to collectively discover new mathematical results through open interaction, achieving 12 new state-of-the-art outcomes including raising the 11-dimensional kissing number lower bound from 593 to 604.
-
AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agents
AI CFD Scientist autonomously discovers a Spalart-Allmaras runtime correction reducing lower-wall Cf RMSE by 7.89% on the periodic hill at Reh=5600 while using a vision-language gate to detect 14 of 16 silent failures missed by solver checks.
-
Knows: Agent-Native Structured Research Representations
Knows uses a YAML sidecar specification to provide structured, agent-consumable representations of research papers, yielding large accuracy gains for small LLMs on comprehension tasks and rapid community adoption via a public hub.
-
Agentic-Ideation: Sample Efficient Agentic Trajectories Synthesis for Scientific Ideation Agents
Agentic-Ideation uses oracle-guided multi-agent synthesis to generate efficient training trajectories for scientific ideation agents, reporting 11.91% quality gains and over 10x sample efficiency versus workflow baselines.
-
Automated reproducibility assessments in the social and behavioral sciences using large language models
LLMs match original qualitative conclusions in 80% of 180 studies and effect sizes in 24%, performing similarly to humans in a tested subset, positioning them as a screening tool rather than a full replacement.
-
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
Arbor combines a coordinator, executors, and a hypothesis tree to enable cumulative autonomous research, outperforming Codex and Claude Code by over 2.5x on six real tasks and reaching 86.36% Any Medal on MLE-Bench Lite.
-
Signal-Driven Observation for Long-Horizon Web Agents
Signal-Driven Observation decouples observation from action frequency in long-horizon web agents by invoking selective task-relevant DOM reads only on signals such as URL changes or action failures.
-
AgentJet: A Distributed Swarm Training Framework for Agentic Reinforcement Learning
A client-server swarm framework lets arbitrary agent code run on detached machines while shared servers train it, and context-timeline merging cuts actor-update time by 6.25x on AppWorld.
-
How Far Are We From True Auto-Research?
ResearchArena shows that agent-generated papers fail top-tier acceptance standards primarily due to fabricated results, underpowered experiments, and plan-execution mismatches that vary sharply by agent.
-
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.
-
Learning to Predict Future-Aligned Research Proposals with Language Models
Time-sliced training and a Future Alignment Score make LLMs generate research proposals that better anticipate post-cutoff published directions, with reported gains and two implemented proposals.
-
DeepReviewer 2.0: A Traceable Agentic System for Auditable Scientific Peer Review
An agentic system produces traceable review packages and an un-finetuned 196B model using it covers more major issues than Gemini-3.1-Pro on 134 ICLR 2025 submissions while winning most blind comparisons to human committees.
-
GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis
GenoMAS deploys six specialized LLM agents with guided planning to preprocess transcriptomic data and identify genes, reaching 89.13% composite similarity and 60.48% F1 on the GenoTEX benchmark while outperforming prior methods.
-
Clarus: Coordinating Autonomous Research Agents toward Web-Scale Scientific Collaboration
Clarus is a four-layer collaboration infrastructure with a project-agent-resource model that reformulates research as an open, traceable, multi-participant process.
-
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.
-
AiraXiv: An AI-Driven Open-Access Platform for Human and AI Scientists
AiraXiv is a proposed AI-driven platform for open preprints that supports human and AI authors with interactive UI and MCP-based interactions, validated by serving as the submission system for ICAIS 2025.
-
pAI/MSc: ML Theory Research with Humans on the Loop
pAI/MSc is a customizable multi-agent system that reduces human steering by orders of magnitude when turning a hypothesis into a literature-grounded, mathematically established, experimentally supported manuscript draft in ML theory.
-
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.
-
Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator
The paper proposes a four-role framework for LLMs in scientific innovation and reviews methods, benchmarks, and limitations across Assistant, Collaborator, Scientist, and Evaluator roles.
-
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.