Copertina

Why LLMs Aren't Scientists Yet: Lessons from Four Autonomous Research Attempts

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Trehan, Dhruv, Chopra, Paras
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

METIS: Mentoring Engine for Thoughtful Inquiry & Solutions
di: Kumar, Abhinav Rajeev, et al.
Pubblicazione: (2026)

The Sequential Edge: Inverse-Entropy Voting Beats Parallel Self-Consistency at Matched Compute
di: Sharma, Aman, et al.
Pubblicazione: (2025)

Think Just Enough: Sequence-Level Entropy as a Confidence Signal for LLM Reasoning
di: Sharma, Aman, et al.
Pubblicazione: (2025)

EsoLang-Bench: Evaluating Genuine Reasoning in Large Language Models via Esoteric Programming Languages
di: Sharma, Aman, et al.
Pubblicazione: (2026)

Hybrid Neural World Models
di: Lakshmanan, Pranav, et al.
Pubblicazione: (2026)

Datasheets Aren't Enough: DataRubrics for Automated Quality Metrics and Accountability
di: Winata, Genta Indra, et al.
Pubblicazione: (2025)

Discovering Reinforcement Learning Interfaces with Large Language Models
di: Jaswal, Akshat Singh, et al.
Pubblicazione: (2026)

Building Interpretable Models for Moral Decision-Making
di: Goel, Mayank, et al.
Pubblicazione: (2026)

Who Said Neural Networks Aren't Linear?
di: Berman, Nimrod, et al.
Pubblicazione: (2025)

Detecting Jailbreak Attempts in Clinical Training LLMs Through Automated Linguistic Feature Extraction
di: Nguyen, Tri, et al.
Pubblicazione: (2026)

ALAS: Autonomous Learning Agent for Self-Updating Language Models
di: Atreja, Dhruv
Pubblicazione: (2025)

Scaling Is All You Need: Autonomous Driving with JAX-Accelerated Reinforcement Learning
di: Harmel, Moritz, et al.
Pubblicazione: (2023)

Future Is Unevenly Distributed: Forecasting Ability of LLMs Depends on What We're Asking
di: Karkar, Chinmay, et al.
Pubblicazione: (2025)

Zero-Shot Confidence Estimation for Small LLMs: When Supervised Baselines Aren't Worth Training
di: Nguyen, Luong N.
Pubblicazione: (2026)

CauScientist: Teaching LLMs to Respect Data for Causal Discovery
di: Peng, Bo, et al.
Pubblicazione: (2026)

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows
di: Xu, Wanghan, et al.
Pubblicazione: (2025)

Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs
di: Salem, Ahmed, et al.
Pubblicazione: (2026)

Towards a Medical AI Scientist
di: Wu, Hongtao, et al.
Pubblicazione: (2026)

AlphaLab: Autonomous Multi-Agent Research Across Optimization Domains with Frontier LLMs
di: Hogan, Brendan R., et al.
Pubblicazione: (2026)

Do Two AI Scientists Agree?
di: Fu, Xinghong, et al.
Pubblicazione: (2025)

Learning to Correct: Calibrated Reinforcement Learning for Multi-Attempt Chain-of-Thought
di: Ildiz, Muhammed Emrullah, et al.
Pubblicazione: (2026)

Robust Yet Efficient Conformal Prediction Sets
di: Zargarbashi, Soroush H., et al.
Pubblicazione: (2024)

Learning from Failures in Multi-Attempt Reinforcement Learning
di: Chung, Stephen, et al.
Pubblicazione: (2025)

Why Aren't There More Whistleblowers?
di: Robert A. Aronowitz
Pubblicazione: (2024)

MaD-Scientist: AI-based Scientist solving Convection-Diffusion-Reaction Equations Using Massive PINN-Based Prior Data
di: Kang, Mingu, et al.
Pubblicazione: (2024)

The AI Data Scientist
di: Akimov, Farkhad, et al.
Pubblicazione: (2025)

Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMs
di: Salimi, Moein, et al.
Pubblicazione: (2026)

Discovering Spoofing Attempts on Language Model Watermarks
di: Gloaguen, Thibaud, et al.
Pubblicazione: (2024)

Causal Feature Selection for Responsible Machine Learning
di: Moraffah, Raha, et al.
Pubblicazione: (2024)

Geometry of Human Perceptual Domains Emerges Transiently in LLM Representations
di: Singh, Simardeep, et al.
Pubblicazione: (2026)

See, Symbolize, Act: Grounding VLMs with Spatial Representations for Better Gameplay
di: Baghel, Ashish, et al.
Pubblicazione: (2026)

MILP-SAT-GNN: Yet Another Neural SAT Solver
di: Cardillo, Franco Alberto, et al.
Pubblicazione: (2025)

Can LLMs Effectively Leverage Graph Structural Information through Prompts, and Why?
di: Huang, Jin, et al.
Pubblicazione: (2023)

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks
di: Li, Ang, et al.
Pubblicazione: (2025)

Not Yet AlphaFold for the Mind: Evaluating Centaur as a Synthetic Participant
di: Namazova, Sabrina, et al.
Pubblicazione: (2025)

ARIES: Autonomous Reasoning with LLMs on Interactive Thought Graph Environments
di: Gimenes, Pedro, et al.
Pubblicazione: (2025)

When Visuals Aren't the Problem: Evaluating Vision-Language Models on Misleading Data Visualizations
di: Lalai, Harsh Nishant, et al.
Pubblicazione: (2026)

Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models
di: Shi, Zhengliang, et al.
Pubblicazione: (2025)

ThinkSwitch: Context Distillation with LoRA and Weight Interpolation for Specific-Purpose Reasoning Tasks
di: Saini, Dhruv, et al.
Pubblicazione: (2026)

Collaborative Yet Personalized Policy Training: Single-Timescale Federated Actor-Critic
di: Wang, Leo Muxing, et al.
Pubblicazione: (2026)