AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents
Paper
•
2512.23343
•
Published
•
27
2026
-
-
Valori: A Deterministic Memory Substrate for AI Systems
Paper • 2512.22280 • Published • 3 -
Improving Multi-step RAG with Hypergraph-based Memory for Long-Context Complex Relational Modeling
Paper • 2512.23959 • Published • 103 -
Nested Learning: The Illusion of Deep Learning Architectures
Paper • 2512.24695 • Published • 35 -
Fast-weight Product Key Memory
Paper • 2601.00671 • Published • 4 -
Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits
Paper • 2512.20578 • Published • 76 -
SimpleMem: Efficient Lifelong Memory for LLM Agents
Paper • 2601.02553 • Published • 28 -
Confidence Estimation for LLMs in Multi-turn Interactions
Paper • 2601.02179 • Published • 14 -
Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem
Paper • 2512.24873 • Published • 101 -
OpenNovelty: An LLM-powered Agentic System for Verifiable Scholarly Novelty Assessment
Paper • 2601.01576 • Published • 10 -
Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models
Paper • 2512.24618 • Published • 137 -
Scaling Open-Ended Reasoning to Predict the Future
Paper • 2512.25070 • Published • 15 -
Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process
Paper • 2512.23988 • Published • 15 -
Figure It Out: Improving the Frontier of Reasoning with Active Visual Thinking
Paper • 2512.24297 • Published • 5 -
Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space
Paper • 2512.24617 • Published • 56 -
Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization
Paper • 2512.24615 • Published • 113 -
SenseNova-MARS: Empowering Multimodal Agentic Reasoning and Search via Reinforcement Learning
Paper • 2512.24330 • Published • 33 -
The Reasoning-Creativity Trade-off: Toward Creativity-Driven Problem Solving
Paper • 2601.00747 • Published • 18 -
Diversity or Precision? A Deep Dive into Next Token Prediction
Paper • 2512.22955 • Published • 7 -
Can We Trust AI Explanations? Evidence of Systematic Underreporting in Chain-of-Thought Reasoning
Paper • 2601.00830 • Published • 2 -
Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time Scaling
Paper • 2601.02346 • Published • 25 -
BEDA: Belief Estimation as Probabilistic Constraints for Performing Strategic Dialogue Acts
Paper • 2512.24885 • Published • 4 -
CPPO: Contrastive Perception for Vision Language Policy Optimization
Paper • 2601.00501 • Published • 6 -
Project Ariadne: A Structural Causal Framework for Auditing Faithfulness in LLM Agents
Paper • 2601.02314 • Published • 1 -
MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoning
Paper • 2512.23412 • Published • 37 -
UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision
Paper • 2601.03193 • Published • 44 -
CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving
Paper • 2601.01874 • Published • 18 -
WebGym: Scaling Training Environments for Visual Web Agents with Realistic Tasks
Paper • 2601.02439 • Published • 15 -
Digital Twin AI: Opportunities and Challenges from Large Language Models to World Models
Paper • 2601.01321 • Published • 17 -
Large Reasoning Models Are (Not Yet) Multilingual Latent Reasoners
Paper • 2601.02996 • Published • 4 -
NitroGen: An Open Foundation Model for Generalist Gaming Agents
Paper • 2601.02427 • Published • 41 -
COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs
Paper • 2601.01836 • Published • 7 -
Steerability of Instrumental-Convergence Tendencies in LLMs
Paper • 2601.01584 • Published -
Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting
Paper • 2601.02151 • Published • 98 -
Evolving Programmatic Skill Networks
Paper • 2601.03509 • Published • 75 -
Atlas: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning
Paper • 2601.03872 • Published • 40 -
ROI-Reasoning: Rational Optimization for Inference via Pre-Computation Meta-Cognition
Paper • 2601.03822 • Published • 22 -
Agentic Rubrics as Contextual Verifiers for SWE Agents
Paper • 2601.04171 • Published • 10 -
MDAgent2: Large Language Model for Code Generation and Knowledge Q&A in Molecular Dynamics
Paper • 2601.02075 • Published • 7 -
Why LLMs Aren't Scientists Yet: Lessons from Four Autonomous Research Attempts
Paper • 2601.03315 • Published • 5 -
MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents
Paper • 2601.03236 • Published • 2 -
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
Paper • 2601.05242 • Published • 193 -
RelayLLM: Efficient Reasoning via Collaborative Decoding
Paper • 2601.05167 • Published • 27 -
AT^2PO: Agentic Turn-based Policy Optimization via Tree Search
Paper • 2601.04767 • Published • 26 -
Agent-as-a-Judge
Paper • 2601.05111 • Published • 16 -
The Illusion of Specialization: Unveiling the Domain-Invariant "Standing Committee" in Mixture-of-Experts Models
Paper • 2601.03425 • Published • 15 -
One Sample to Rule Them All: Extreme Data Efficiency in RL Scaling
Paper • 2601.03111 • Published • 8 -
DocDancer: Towards Agentic Document-Grounded Information Seeking
Paper • 2601.05163 • Published • 4 -
AgentDevel: Reframing Self-Evolving LLM Agents as Release Engineering
Paper • 2601.04620 • Published • 1 -
Scaling Behavior Cloning Improves Causal Reasoning: An Open Model for Real-Time Video Game Playing
Paper • 2601.04575 • Published • 6 -
Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization
Paper • 2601.05432 • Published • 159 -
The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning
Paper • 2601.06002 • Published • 47 -
EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis
Paper • 2601.05808 • Published • 34 -
Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards
Paper • 2601.06021 • Published • 39 -
AgentOCR: Reimagining Agent History via Optical Self-Compression
Paper • 2601.04786 • Published • 27 -
Can We Predict Before Executing Machine Learning Agents?
Paper • 2601.05930 • Published • 25 -
Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency
Paper • 2601.05905 • Published • 16 -
An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift
Paper • 2601.05882 • Published • 19 -
SmartSearch: Process Reward-Guided Query Refinement for Search Agents
Paper • 2601.04888 • Published • 8 -
DR-LoRA: Dynamic Rank LoRA for Mixture-of-Experts Adaptation
Paper • 2601.04823 • Published • 5 -
Over-Searching in Search-Augmented Large Language Models
Paper • 2601.05503 • Published • 5 -
Memory Matters More: Event-Centric Memory as a Logic Map for Agent Searching and Reasoning
Paper • 2601.04726 • Published • 4 -
TCAndon-Router: Adaptive Reasoning Router for Multi-Agent Collaboration
Paper • 2601.04544 • Published • 4 -
Legal Alignment for Safe and Ethical AI
Paper • 2601.04175 • Published • 3 -
TowerMind: A Tower Defence Game Learning Environment and Benchmark for LLM as Agents
Paper • 2601.05899 • Published • 2 -
Distilling Feedback into Memory-as-a-Tool
Paper • 2601.05960 • Published • 1 -
IIB-LPO: Latent Policy Optimization via Iterative Information Bottleneck
Paper • 2601.05870 • Published • 2