Glite ARF introduces a verifier-driven three-role framework for parallel LLM coding agents, demonstrated by first- and second-place finishes in the BEA 2026 vocabulary-difficulty shared task across three languages with 29.9-35.9% RMSE reduction at ~$450 API cost.
hub
arXiv preprint arXiv:2505.13259 , year =
17 Pith papers cite this work. Polarity classification is still indexing.
17
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
Camyla autonomously generates research proposals, experiments, and manuscripts in medical image segmentation, outperforming baselines on 24 of 31 recent datasets while producing 40 human-reviewed papers.
LLM-native figures embed provenance and enable direct LLM interaction with scientific visualizations to accelerate discovery and improve reproducibility.
k-server-bench formulates potential-function discovery for the k-server conjecture as a code-based inequality-satisfaction task; current agents fully solve the resolved k=3 case and reduce violations on the open k=4 case.
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
STRIDE is a self-reflective agent framework that improves accuracy, OOD robustness, and structural recovery in LLM-based symbolic regression by integrating generation, evaluation, repair, and diversity-preserving memory.
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.
SciLens introduces an evidence-conditioned atomic entailment framework that grounds claims to modality-specific witnesses in tables and figures, achieving 79.2% macro-F1 on SciClaimEval.
EvoSci combines evolutionary multi-agent collaboration with knowledge graphs to produce scientific ideas that score higher on LLM peer-review metrics than baselines.
CVEvolve is a zero-code LLM agent harness that autonomously discovers algorithms for scientific image tasks including registration, peak detection, and segmentation, reporting improvements over baselines via iterative search and holdout evaluation.
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.
Outcome evidence improves LLM accuracy on scientific feasibility assessment more consistently than experiment descriptions, which introduce brittleness under partial context.
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.
Under fixed token budget on Circle Packing, deeper per-candidate reasoning beats generating more shallow candidates, and capable models produce evaluation hacks at higher rates.
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.
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.
MIRAI predicts 5-year PageRank and citation impact from paper title/abstract/date with Spearman's ρ 0.47/0.62, and generates ideas judged 4:3 more impactful by LLM.
citing papers explorer
-
Glite ARF: Verifier-Driven Research with Parallel LLM Coding Agents
Glite ARF introduces a verifier-driven three-role framework for parallel LLM coding agents, demonstrated by first- and second-place finishes in the BEA 2026 vocabulary-difficulty shared task across three languages with 29.9-35.9% RMSE reduction at ~$450 API cost.
-
Camyla: Scaling Autonomous Research in Medical Image Segmentation
Camyla autonomously generates research proposals, experiments, and manuscripts in medical image segmentation, outperforming baselines on 24 of 31 recent datasets while producing 40 human-reviewed papers.
-
Figures as Interfaces: Toward LLM-Native Artifacts for Scientific Discovery
LLM-native figures embed provenance and enable direct LLM interaction with scientific visualizations to accelerate discovery and improve reproducibility.
-
$k$-server-bench: Automating Potential Discovery for the $k$-Server Conjecture
k-server-bench formulates potential-function discovery for the k-server conjecture as a code-based inequality-satisfaction task; current agents fully solve the resolved k=3 case and reduce violations on the open k=4 case.
-
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
-
STRIDE: A Self-Reflective Agent Framework for Reliable Automatic Equation Discovery
STRIDE is a self-reflective agent framework that improves accuracy, OOD robustness, and structural recovery in LLM-based symbolic regression by integrating generation, evaluation, repair, and diversity-preserving memory.
-
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.
-
SciLens: Multi-modal Scientific Claim Verification with Agentic Entailment and Grounding
SciLens introduces an evidence-conditioned atomic entailment framework that grounds claims to modality-specific witnesses in tables and figures, achieving 79.2% macro-F1 on SciClaimEval.
-
EvoSci: A Bio-Inspired Multi-Agent Framework for the Evolution of Scientific Discovery
EvoSci combines evolutionary multi-agent collaboration with knowledge graphs to produce scientific ideas that score higher on LLM peer-review metrics than baselines.
-
CVEvolve: Autonomous Algorithm Discovery for Unstructured Scientific Data Processing
CVEvolve is a zero-code LLM agent harness that autonomously discovers algorithms for scientific image tasks including registration, peak detection, and segmentation, reporting improvements over baselines via iterative search and holdout evaluation.
-
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.
-
Experiments or Outcomes? Probing Scientific Feasibility in Large Language Models
Outcome evidence improves LLM accuracy on scientific feasibility assessment more consistently than experiment descriptions, which introduce brittleness under partial context.
-
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.
-
Effective Harness Engineering for Algorithm Discovery with Coding Agents
Under fixed token budget on Circle Packing, deeper per-candidate reasoning beats generating more shallow candidates, and capable models produce evaluation hacks at higher rates.
-
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.
-
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.
-
MIRAI: Prediction and Generation of High-Impact Academic Research
MIRAI predicts 5-year PageRank and citation impact from paper title/abstract/date with Spearman's ρ 0.47/0.62, and generates ideas judged 4:3 more impactful by LLM.