Artificial Intelligence Paper Rankings

ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence

Why LLMs Fail at Causal Discovery and How Interventional Agents Escape

Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure

AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation

Entropy Distribution as a Fingerprint for Hallucinations in Generative Models

Calibrating Conservatism for Scalable Oversight

Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems

Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases

When Context Flips, Safety Breaks: Diagnosing Brittle Safety in Aligned Language Models

Inference Time Context Sparsity: Illusion or Opportunity?

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

SIA: Self Improving AI with Harness & Weight Updates

Detecting Is Not Resolving: The Monitoring Control Gap in Retrieval Augmented LLMs

Neuro-Inspired Inverse Learning for Planning and Control

Learning to Search and Searching to Learn for Generalization in Planning

Human-like in-group bias in instruction-tuned language model agents

CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents

RULER: Representation-Level Verification of Machine Unlearning

What Makes Chain-of-Thought Work at Probe Time? Local Co-occurrence Rather Than Global Derivation

Understanding and Mitigating Premature Confidence for Better LLM Reasoning

The Attribution Blind Spot: Detecting When Language Models Rely on Memory Rather Than Retrieved Context

DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes

Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention

Beyond the Frontier: Stochastic Backtracking for Efficient Test-Time Scaling

Fundamental Limitation in Explaining AI

Is Capability a Liability? More Capable Language Models Make Worse Forecasts When It Matters Most

Forecasting Scientific Progress with Artificial Intelligence

Is Agent Memory a Database? Rethinking Data Foundations for Long-Term AI Agent Memory

The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems

Voluntary Collusion with Secret Tools in Competing LLM Agents

LACUNA: Safe Agents as Recursive Program Holes

Better Accuracies, Worse Reasoning: A Step-Level Audit of Medical Chain-of-Thought Distillation

AIBuildAI-2: A Knowledge-Enhanced Agent for Automatically Building AI Models

A governance horizon for ethical-use constraints in open-weight AI models

Credit Assignment with Resets in Language Model Reasoning

PolyFusionAgent: A Multimodal Foundation Model and Autonomous AI Assistant for Polymer Property Prediction and Inverse Design

UnityMAS-O: A General RL Optimization Framework for LLM-Based Multi-Agent Systems

LipoAgent: Coordinating Fine-Tuned LLM Agents for Safer Lipid Design

CaMBRAIN: Real-time, Continuous EEG Inference with Causal State Space Models

Learning to Reason Efficiently with A* Post-Training

Zipping the Thought: When and How Compressed Reasoning Data Works in LLM Post-Training

CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning

Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications

From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills

MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems

AI Cartography: Mapping the Latent Landscape of AI Benchmark Ecosystems

EVE-Agent: Evidence-Verifiable Self-Evolving Agents

Composition Collapse: Stable Factual Knowledge Does Not Imply Compositional Reasoning

LiveBrowseComp: Are Search Agents Searching, or Just Verifying What They Already Know?

SafeMed-R1: Clinician-Audited Safety and Ethics Alignment for Medical Large Language Models

ZipRL: Adaptive Multi-Turn Context Compression with Hindsight Response Replay

CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists

From Static Context to Calibrated Interactive RL: Mitigating Distribution Shift in Multi-turn Dialogue with Aligned Simulator

OpenURMA: A Clean-Room Open Implementation of the Unified Bus Protocol

Plant, Persist, Trigger: Sleeper Attack on Large Language Model Agents

Beyond a Single Direction: Chain-of-Thought Disrupts Simple Steering of Refusal

Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM Agents

SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent

The Deterministic Horizon: Impossibility Results as Design Specifications for Trustworthy AI Systems

Thinking as Compression: Your Reasoning Model is Secretly a Context Compressor

Proper Scoring Rules for Agentic Uncertainty Quantification

Bridging the Detection-to-Abstention Gap in Reasoning Models under Insufficient Information

LaneRoPE: Positional Encoding for Collaborative Parallel Reasoning and Generation

StructBreak: Structural Cognitive Overload-Induced Safety Failures in MLLMs

Behavioural Analysis of Alignment Faking

From Fact Overwriting to Knowledge Evolution: Causal Editing via On-Policy Self-Distillation

Advancing Creative Physical Intelligence in Large Multimodal Models

Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning

HyperGuide: Hyperbolic Guidance for Efficient Multi-Step Reasoning in Large Language Models

PALoRA: Projection-Adaptive LoRA for Preserving Reasoning in Large Language Models

Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows

Position: AI Safety Requires Effective Controllability

Hypothesis Generation and Inductive Inference in Children and Language Models

Which Changes Matter? Towards Trustworthy Legal AI via Relevance-Sensitive Evaluation and Solver-Grounded Reasoning

MemCog: From Memory-as-Tool to Memory-as-Cognition in Conversational Agents

PEAM: Parametric Embodied Agent Memory through Contrastive Internalization of Experience in Minecraft

A Unified Framework for the Evaluation of LLM Agentic Capabilities

Can LLMs Introspect? A Reality Check

AMEL: Accumulated Message Effects on LLM Judgments

Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systems

GENSTRAT: Toward a Science of Strategic Reasoning in Large Language Models

Continual Model Routing in Evolving Model Hubs

Compiling Agentic Workflows into LLM Weights: Near-Frontier Quality at Two Orders of Magnitude Less Cost

Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy

Do Clinical Models Change Treatment Decisions?

AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning

How Well Do Models Follow Their Constitutions?

Trust but Verify: Prover-Verifier Deliberation for Selective LLM Prediction

A Policy-Driven Runtime Layer for Agentic LLM Serving

From Accounting to Coordination: A Virtual Water-Aware Electricity-Computation-Water Nexus Framework for Data Center Dispatch

Emotional intelligence in large language models is fragmented across perception, cognition, and interaction

Geometry of Human Perceptual Domains Emerges Transiently in LLM Representations

MUSE: Benchmarking Manufacturable, Functional, and Assemblable Text-to-CAD Generation

MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research

GlobalDentBench: A Multinational Benchmark for Evaluating LLM Clinical Reasoning in Dentistry with Expert Calibration

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs

AGORA: Adapter-Grounded Observation-Action Retention for Inference-Free Prompt Compression in LLM Agents

Search-E1: Self-Distillation Drives Self-Evolution in Search-Augmented Reasoning

TRACER: Turn-level Regret Matching with Inner Reinforcement Credit for Cooperative Multi-LLM Reasoning

PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning

EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents

Reasoning Matters: Mitigate Hallucination in Multimodal Large Reasoning Models via Reasoning-Conditioned Preference Optimization

Can AI Make Conflicts Worse? An Alignment Failure in LLM Deployment Across Conflict Contexts

Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs

JobBench: Aligning Agent Work With Human Will

CODESKILL: Learning Self-Evolving Skills for Coding Agents

A Sober Look at Agentic Misalignment in Automated Workflows

Insuring Every Action: An Authority Frontier Framework for Runtime Actuarial Control of Autonomous AI Agents

Satisfiability Solving with LLMs: A Matched-Pair Evaluation of Reasoning Capability

When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs

Verifiable Benchmarking of Long-Horizon Spatial Biology

Anchor: Mitigating Artifact Drift in Agent Benchmark Generation

ConceptM$^3$oE: Concept-Guided Multimodal Mixture of Experts for Interpretable Computational Pathology

Personalizing Embodied Multimodal Large Language Model Agents over Long-term User Interactions

Retrying vs Resampling in AI Control

From Model Scaling to System Scaling: Scaling the Harness in Agentic AI

Clustering as Reasoning: A $k$-Means Interpretation of Chain-of-Thought Graph Learning

On the Origin of Synthetic Information by Means of Steganographic Inheritance

Multi-Adapter Representation Interventions via Energy Calibration

Meta-Agent: From Task Descriptions to Verified Multi-Agent Systems

Automatic Layer Selection for Hallucination Detection

Can Broad Biomedical Knowledge be Contextualized into Scenario-Grounded Propositions?

MemFail: Stress-Testing Failure Modes of LLM Memory Systems

LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems

TIGER: Text-Informed Generalized Enzyme-Reaction Retrieval

VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions

Measuring Progress Toward AGI: A Cognitive Framework

Back to Parsimonious Latents: Learning Task-Centric World Models from Visual Foundations

Relevant Is Not Warranted: Evidence-Force Calibration for Cited RAG

AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery

Tree of Thoughts as a Classical Heuristic Search Problem: Formal Foundations and Design Patterns

Do Agents Think Deeper? A Mechanistic Investigation of Layer-Wise Dynamics in Sequential Planning

FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization

Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models

Look on Demand: A Cognitive Scheduling Framework for Visual Evidence Acquisition in Multimodal Reasoning

MuCRASP: Multimodal Chain-of-thought Reasoning aware Structured Pruning

Mitigating Object Hallucinations in Vision-Language Models through Region-Aware Attention Recalibration

MolLingo: Molecule-Native Representations for LLM-Powered Scientific Agents

Mind the Tool Failures: Achieving Synergistic Tool Gains for Medical Agents

Test-Time Deep Thinking to Explore Implicit Rules

Prompt Codebooks: Discrete Compositional Optimization for Language Model Instruction Refinement

Energy Shields for Fairness

PANDO: Efficient Multimodal AI Agents via Online Skill Distillation

Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations

Uncertainty Reasoning with Large Language Models for Explainable Disease Diagnosis

Plan Before Search: Search Agents Need Plan

VeriTrip: A Verifiable Benchmark for Travel Planning Agents over Unstructured Web Corpora

Localizing Input Uncertainty Quantification for Large Language Models via Shapley Values

Where Rollouts Begin: Low-Load, High-Leverage First-Token Diversification for RLVR

MedGuideX: Internalizing Decision Logic from Executable Guidelines into Large Language Models for Clinical Reasoning

Scaling, Benchmarking, and Reasoning of Vision-Language Agents for Mobile GUI Navigation

Beyond Final Answers: Auditing Trajectory-Level Hallucinations in Multi-Agent Industrial Workflows

One Policy, Infinite NPCs: Persona-Traceable Shared RL Policies for Scalable Game Agents

EDGE-OPD: Internalizing Privileged Context with Evidence Guided On-Policy Distillation

Confidence-Orchestrated Self-Evolution against Uncertain LLM Feedback

Learning When to Optimize: Verified Optimization Skills from Expert GPU-Kernel Lineages

Lattice theory and algebraic models for deep convolutional learning based on mathematical morphology

You Live More Than Once: Towards Hierarchical Skill Meta-Evolving

Revealing Algorithmic Deductive Circuits for Logical Reasoning

HRBench: Benchmarking and Understanding Thinking-Mode Switch Strategies in Hybrid-Reasoning LLMs

Query Symbolically or Retrieve Semantically? A Dataset and Method for Semi-Structured Question Answering

MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection

SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills

BlazeEdit: Generalist Image Editing on Mobile Devices with Image-to-Image Diffusion Models

Boosting Inference with Guided Reasoning: Stochastic Exploration for Recursive Models

Measuring Reasoning Quality in LLMs: A Multi-Dimensional Behavioral Framework

NeurIPS: Neuro-anatomical Inductive Priors for Sphere-based Brain Decoding

Design and Report Benchmarks for Knowledge Work

Behind EvoMap: Characterizing a Self-Evolving Agent-to-Agent Collaboration Network

Deconstructing Spatial Complexity: Hierarchical Decomposition for LLM Spatial Reasoning

Representation Without Control: Testing the Realization Effect in Language Models

Bandwidth-Efficient and Privacy-Preserving Edge-Cloud Many-to-Many Speech Translation

Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments

Asking Is Not Enough: Protocol Sensitivity in LLM Confidence Calibration

DREAM-R: Multimodal Speculative Reasoning with RL-Based Refined Drafting, Precise Verification, and Fully Parallel Execution

Towards end-to-end LLM-based censoring-aware survival analysis

Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement Learning

OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing

Generating Robust Portfolios of Optimization Models using Large Language Models

Agentic Proving for Program Verification

When Mean CE Fails: Median CE Can Better Track Language Model Quality

Whose Alignment? Comparing LLM Process Alignment Across Diverse Organizational Decision Contexts

SPACE: Unifying Symmetric and Asymmetric Routing Problems for Generalist Neural Solver

Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World

Beyond Inference-Only Deployment: Comparing Weight-Based Consolidation Against Cascading Compaction

DarkForest: Less Talk, Higher Accuracy for Multi-Agent LLMs

Towards Faithful Agentic XAI: A Verification Method and an Open-World Benchmark for Better Model Faithfulness

Co-ReAct: Rubrics as Step-Level Collaborators for ReAct Agents

AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions

Natural Language Query to Configuration for Retrieval Agents

AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image Prompters

JT-SAFE-V2: Safety-by-Design Foundation Model with World-Context Data

A Fixed-Budget, Cluster-Aware Standard for LLM-as-a-Judge Evaluation: A Multi-Hop RAG Stress Test

StepOPSD: Step-Aware Online Preference Distillation for Agent Reinforcement Learning

DART: Semantic Recoverability for Structured Tool Agents