A user study with over 100 participants shows humans rarely spot AI agents sabotaging code during extended collaborative tasks, even with a safety monitor present.
hub
ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models , booktitle =
12 Pith papers cite this work, alongside 28 external citations. Polarity classification is still indexing.
12
Pith papers citing it
28
external citations · OpenAlex
hub tools
representative citing papers
Builds a 2M-contribution graph from 230k papers with 12.5M prerequisite links and reports 0.48 MAP on temporal backtesting for predicting enabling technologies.
A new benchmark (IG-Bench) reveals that LLM-based scientists fail at compositional lineage reasoning, with the best system reaching only 27.3% exact accuracy.
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.
Graph2Idea builds dynamic knowledge graphs from retrieved literature to supply compact, relational contexts that guide LLMs in generating novel, feasible, and high-quality scientific ideas, outperforming flat-text baselines on automatic metrics.
HyBIRD adds point, cone, and factorized hyperbolic bridges over a frozen dense retriever for methodology inspiration retrieval, reaching 59.034 mAP on the MIR benchmark while producing query need profiles and evidence bundles.
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.
Structuring LLM hypothesis generation around deductive-nomological explanation, causal processes, and universals is reported to beat direct prompting, with two generated ideas implemented as the CTAT and HALO algorithms.
EvoGens uses rank-based mutation, semantic-aware crossover, and lightweight evaluation to evolve populations of LLM-generated scientific ideas, boosting novelty and diversity metrics.
Proposes AI-driven simulations for literary-historical experiments and reports preliminary text-generation results claiming the first limited in-distribution outputs matching human novels.
SciAtlas builds a large-scale multi-disciplinary academic knowledge graph and a neuro-symbolic retrieval system to support automated scientific research tasks such as literature review and idea positioning.
WisPaper integrates semantic search with agent-based validation, library organization, and personalized AI feeds into a closed-loop system that improves academic paper discovery and long-term awareness.
citing papers explorer
-
Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage?
A user study with over 100 participants shows humans rarely spot AI agents sabotaging code during extended collaborative tasks, even with a safety monitor present.
-
The Scientific Contribution Graph: Automated Literature-based Technological Roadmapping at Scale
Builds a 2M-contribution graph from 230k papers with 12.5M prerequisite links and reports 0.48 MAP on temporal backtesting for predicting enabling technologies.
-
Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
A new benchmark (IG-Bench) reveals that LLM-based scientists fail at compositional lineage reasoning, with the best system reaching only 27.3% exact accuracy.
-
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.
-
Graph2Idea:Retrieval-Augmented Scientific Idea Generation with Graph-Structured Contexts
Graph2Idea builds dynamic knowledge graphs from retrieved literature to supply compact, relational contexts that guide LLMs in generating novel, feasible, and high-quality scientific ideas, outperforming flat-text baselines on automatic metrics.
-
HyBIRD: Hyperbolic Bridge Retrieval and Diagnosis for Methodology Inspiration Retrieval
HyBIRD adds point, cone, and factorized hyperbolic bridges over a frozen dense retriever for methodology inspiration retrieval, reaching 59.034 mAP on the MIR benchmark while producing query need profiles and evidence bundles.
-
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.
-
DN-Hypo-Pipeline: An AI-Driven Workflow for Generating Hypotheses using Large Language Models and Scientific Explanations
Structuring LLM hypothesis generation around deductive-nomological explanation, causal processes, and universals is reported to beat direct prompting, with two generated ideas implemented as the CTAT and HALO algorithms.
-
EvoGens: A Population-Based Heuristic Search Framework for Scientific Idea Generation
EvoGens uses rank-based mutation, semantic-aware crossover, and lightweight evaluation to evolve populations of LLM-generated scientific ideas, boosting novelty and diversity metrics.
-
AI as a Tool for Simulation-Based Experiments in Literary Studies
Proposes AI-driven simulations for literary-historical experiments and reports preliminary text-generation results claiming the first limited in-distribution outputs matching human novels.
-
SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research
SciAtlas builds a large-scale multi-disciplinary academic knowledge graph and a neuro-symbolic retrieval system to support automated scientific research tasks such as literature review and idea positioning.
-
WisPaper: Your AI Scholar Search Engine
WisPaper integrates semantic search with agent-based validation, library organization, and personalized AI feeds into a closed-loop system that improves academic paper discovery and long-term awareness.