Memory Is Not Always Needed: Characterizing Conditional Memory in Scientific Reasoning
cs.AI, cs.CL, cs.LG
Submitted: 2026-08-25
Updated: 2026-09-23
Terminology
Sources
- Larimar: Large Language Models with Episodic Memory Control
- MeKi: Memory-based Expert Knowledge Injection for Efficient LLM Scaling
- Language Models (Mostly) Know What They Know
- Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations
- BioProBench: A Corpus and Benchmark for Biological Protocol Reasoning in Autonomous Science
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
- Intern-S1: A Scientific Multimodal Foundation Model
- Solving math word problems with process- and outcome-based feedback
- From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery
- Beyond Conditional Computation: Retrieval-Augmented Genomic Foundation Models with Gengram
- Personalized Large Language Model Assistant with Evolving Conditional Memory
- Augmenting Molecular Language Models with Local $n$-gram Memory
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection