Artificial Intelligence Paper Rankings

Zero knowledge verification for frontier AI training is possible

Beyond One-shot: AI Agents for Learning in Field Experiments

Decomposing how prompting steers behavior

LAP: An Agent-to-Instrument Protocol for Autonomous Science

Thinking Past the Answer: Evaluating Harmful Overthinking in Large Reasoning Models

Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments

Closing the Loop on Latent Reasoning via Test-Time Reconstruction

Scaling Self-Evolving Agents via Parametric Memory

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage?

The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development?

Towards World Models in Biomedical Research

Forget Attention: Importance-Aware Attention Is All You Need

Agents' Last Exam

EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning

Gender-Dependent Diagnostic Substitution in LLM Medical Triage: Same Symptoms, Unequal Urgency

What Benchmarks Don't Measure: The Case for Evaluating Abstention Competence in Autonomous Agents

MIRAGE: Mobile Agents with Implicit Reasoning and Generative World Models

The Reliability Gap in Benchmark Auditing: Distribution Shift and Scale as Failure Modes of Contamination Detection

Don't Gamble, GAMBLe: An Analytical Framework for AI-Driven Research Systems

Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents

Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts

SCI-PRM: A Tool Aware Process Reward Model for Scientific Reasoning Verification

Inference-Time Vulnerability Beyond Shallow Safety: Alignment Along Generation Trajectories

RedKnot: Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention

Can Generalist Agents Automate Data Curation?

Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models

ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning

Reasoning Structure of Large Language Models

Beyond Objective Equivalence: Constraint Injection for LLM-Based Optimization Modeling on Vehicle Routing Problems

EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management

What Makes Interaction Trajectories Effective for Training Terminal Agents?

AURA: Action-Gated Memory for Robot Policies at Constant VRAM

MedCUA-Bench: A Screenshot-Only Benchmark for Clinical Computer-Use Agents

AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?

Beyond Prompt-Based Planning: MCP-Native Graph Planning-based Biomedical Agent System

The Self-Correction Illusion: LLMs Correct Others but Not Themselves

AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents

Beyond Similarity: Trustworthy Memory Search for Personal AI Agents

Benchmark Everything Everywhere All at Once

When Helping Hurts and How to Fix It: Multi-Agent Debate for Data Cleaning

LLM Self-Recognition: Steering and Retrieving Activation Signatures

Fix the Mind, Not the Move: Interpretable AI Assistance via Knowledge-Gap Localization

Minimizing the Hidden Cost of Scales: Graph-Guided Ultra-Low-Bit Quantization for Large Language Models

DeskCraft: Benchmarking Desktop Agents on Professional Workflows and Human-in-the-Loop Collaboration

Assessing the Carbon Emissions and Energy Consumption of U.S. Hyperscale Data Centers

Where does Absolute Position come from in decoder-only Transformers?

CORE: Conflict-Oriented Reasoning for General Multimodal Manipulation Detection

Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses

COMAP: Co-Evolving World Models and Agent Policies for LLM Agents

SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment

Iteris: Agentic Research Loops for Computational Mathematics

POIROT: Interrogating Agents for Failure Detection in Multi-Agent Systems

Code-on-Graph: Iterative Programmatic Reasoning via Large Language Models on Knowledge Graphs

ChatHealthAI: Aligning Electronic Health Record Representations with Large Language Models for Grounded Clinical Reasoning

CP-Agent: Context-Aware Multimodal Reasoning for Cellular Morphological Profiling under Chemical Perturbations

Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search Spaces

SAGE: A Quantitative Evaluation of Socialized Evolution in Agent Ecosystems

Simulate, Reason, Decide: Scientific Reasoning with LLMs for Simulation-Driven Decision Making

TRACE: A Temporal Conditional Estimation for Multimodal Time Series Foundation Models

ClinEnv: An Interactive Multi-Stage Long Horizon EHR Environment for Agents

AgentJet: A Flexible Swarm Training Framework for Agentic Reinforcement Learning

Beyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agents

Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents

Diagnosing Knowledge Gaps in LLM Tool Use: An Agentic Benchmark for Novel API Acquisition

Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads

Amortizing Federated Adaptation: Hypernetwork Driven LoRA for Personalized Foundation Models

Inducing Reasoning Primitives from Agent Traces

MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery

DELTAMEM: Incremental Experience Memory for LLM Agents via Residual Trees

When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents

Stumbling Into AI Emotional Dependence: How Routine AI Interactions Reshape Human Connection

Goedel-Architect: Streamlining Formal Theorem Proving with Blueprint Generation and Refinement

Multilingual Fine-Tuning via Localized Gradient Conflict Resolution

LLM-Evolved Pattern Generators for Optimal Classical Planning

R-APS: Compositional Reasoning and In-Context Meta-Learning for Constrained Design via Reflective Adversarial Pareto Search

Where Should Knowledge Enter? A Layered Framework for Knowledge Infusion in Multimodal Iterative Generative Mo

AIP: A Graph Representation for Learning and Governing Agent Skills

scTranslation: A Comprehensive Benchmark for Single-Cell Multi-Omics Modality Translation

A Pre-Registered Causal Partition of Self-Consistency Elicitation and Reward Design in RLVR

When Should Memory Stay Silent: Measuring Memory-Use Boundaries in Memory-Augmented Conversational Agents

Not All Errors Are Equal: Consequence-Aware Reasoning Compute Allocation

SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training

BehaviorBench: Modeling Real-World User Decisions from Behavioral Traces

Stability vs. Manipulability: Evaluating Robustness Under Post-Decision Interaction in LLM Judges

Entropy Is Not Enough: Unlocking Effective Reinforcement Learning for Visual Reasoning via Vision-Anchored Token Selection

Beyond Output Matching: Preserving Internal Geometry in NVFP4 LLM Distillatio

FALSIFYBENCH: Evaluating Inductive Reasoning in LLMs with Rule Discovery Games

TAPO: Tool-Aware Policy Optimization via Credit Transfer for Multimodal Search Agents

Learning Admissible Heuristics via Cost Partitioning

MapAgent: An Industrial-Grade Agentic Framework for City-scale Lane-level Map Generation

Output Type Before Quality: A Standards-Derived XAI Admissibility Rubric for Autonomous-Driving Safety

ToolChoiceConfusion: Causal Minimal Tool Filtering for Reliable LLM Agents

FIDES: Faithful Inference via Deep Evidence Signals for Retrieval-Memory Conflict in RAG

Mutation Without Variation: Convergence Dynamics in LLM-Driven Program Evolution

Boosting Brain-to-Image Decoding with TRIBE v2 Data Augmentation

From Answers to States: Verifiable Process-Level Evaluation of Chemical Reasoning in Large Language Models

The Shadow Price of Reasoning: Economic Perspective on Optimal Budget Allocation for LLMs

Trivium: Temporal Regret as a First-Class Objective for Causal-Memory Controllers

Overlaying Governance: A Compositional Authorization Framework for Delegation and Scope in Agentic AI

QCFuse: Query-Aware Cache Fusion via Compressed View for Efficient RAG Serving

Cascading Hallucination in Agentic RAG: The CHARM Framework for Detection and Mitigation

SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale

Towards Healthy Evolution: Exploring the Role and Mechanisms of Human-Agent Interaction in Self-Evolving Systems

Do More Agents Help? Controlled and Protocol-Aligned Evaluation of LLM Agent Workflows

SentinelBench: A Benchmark for Long-Running Monitoring Agents

A Framework for Measuring Appropriate Reliance on Set-Valued AI Advice

Edit-R2: Context-Aware Reinforcement Learning for Multi-Turn Image Editing

Handoff Debt: The Rediscovery Cost When Coding Agents Take Over Interrupted Tasks

From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents

Unveiling the Structure of Do-Calculus Reasoning via Derivation Graphs

AdaMEM: Test-Time Adaptive Memory for Language Agents

CogManip: Benchmarking Manipulative Behavior in Multi-Turn Interactions with Large Language Model

Unsupervised Skill Discovery for Agentic Data Analysis

Bridging Auxiliary Constraints to Resolve Instruction Following in Large Reasoning Models

InfoMem: Training Long-Context Memory Agents with Answer-Conditioned Information Gain

Coordination Graphs for Constrained Multi-Agent Reinforcement Learning

ClinicalMC: A Benchmark for Multi-Course Clinical Decision-Making with Large Language Models

Learning Visual Spatial Planning from Symbolic State via Modality-Gap-Aware Self-Distillation

SkillPyramid: A Hierarchical Skill Consolidation Framework for Self-Evolving Agents

How Far Did They Go? The Persuasive Tactics of Covert LLM Agents in a Discontinued Field Experiment

PLAN-S: Bridging Planning with Latent Style Dynamics for Autonomous Driving World Models

Traj-Evolve: A Self-Evolving Multi-Agent System for Patient Trajectory Modeling in Lung Cancer Early Detection

EvoDrive: Pareto Evolution for Safety-Critical Autonomous Driving via Self-Improving LLM Agents

Knowledge Index of Noah's Ark

StepPRM-RTL: Stepwise Process-Reward Guided LLM Fine-Tuning for Enhanced RTL Synthesis

From Risk Classification to Action Plan Remediation: A Guardrail Feedback Driven Framework for LLM Agents

MOC: Multi-Order Communication in LLM-based Multi-Agent Systems

Individual Gain, Collective Loss: Metacognitive Adaptation in AI-Assisted Creativity

Brick-Composer: Using MLLMs for Assembly with Diverse Bricks

Spatial Representation Learning Beyond Pixels: Unifying Raster Data and Vector Semantics for Human-Centric Geospatial Foundation Models

What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems

The Saturation Trap and the Subjectivity of Intervention Timing: Why Affect-Based Triggers and LLM Judges Fail to Time Interventions on Autonomous Agents

HLL: Can Agents Cross Humanity's Last Line of Verification?

Harnessing Generalist Agents for Contextualized Time Series

TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning

PSEBench: A Controllable and Verifiable Benchmark for Evaluating LLMs in Patient Safety Event Triage

SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations

PerceptUI: LLM Agents as Human-Aligned Synthetic Users for UI/UX Evaluation

Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baseline

Solipsistic Superintelligence is Unlikely to be Cooperative

DMF: A Deterministic Memory Framework for Conversational AI Agents

When to Re-Plan: Subgoal Persistence in Hierarchical Latent Reasoning

Tracking the Behavioral Trajectories of Adapting Agents

Humans' ALMANAC: A Human Collaboration Dataset of Action-Level Mental Model Annotations for Agent Collaboration

Seeing Time: Benchmarking Chronological Reasoning and Shortcut Biases in Vision-Language Models

Repair Before Veto: Repair-Augmented Constraint Learning for Contextual Decisions

Tree-Based Formalization of Multi-Agent Complementarity in Human-AI Interactions

Food Noise & False Safety: A Systematic Evaluation of How LLMs Fail to Adapt to Eating Disorder Queries with Clinician Feedback

SMAC-Talk: A Natural Language Extension of the StarCraft Multi-Agent Challenge for Large Language Models

DragOn: A Benchmark and Dataset for Drag-Based GUI Interactions

ToolGate: Token-Efficient Pre-Call Control for Tool-Augmented Vision-Language Agents

Residual Modeling for High-Fidelity Learned Compression of Scientific Data

BigFinanceBench: A Workflow-Grounded Benchmark for Financial-Research Agents

Online Skill Learning for Web Agents via State-Grounded Dynamic Retrieval

DiG-Plan: Mitigating Early Commitment for Tool-Graph Planning via Diffusion Guidance

Can LLMs Write Correct TLA+ Specifications? Evaluating Natural-Language-to-TLA+ Generation

BiasGRPO: Stabilizing Bias Mitigation in High-Variance Reward Landscapes via Group-Relative Policy Optimization

Do Real-World Datasets Contain Natural Experiments? An Empirical Study Using Causal Feature Selection

AICompanionBench: Benchmarking LLMs-as-Judges for AI Companion Safety

Hedge-Bench: Benchmarking Agents on Hard, Realistic Tasks Pertaining to Financial Reasoning

AUDITFLOW: Executable Symbolic Environments for Structured Financial Reporting Verification

StepFinder: A Temporal Semantic Framework for Failure Attribution in Multi-Agent Systems

The Digital Apprentice: A Framework for Human-Directed Agentic AI Development

EpiEvolve: Self-Evolving Agents for Streaming Pandemic Forecasting under Regime Shifts

Integrating Mechanistic and Data-Driven Models for Neurological Disorders through Differentiable Programming

From Long News to Accurate Forecast: Importance-Aware Fusion and PRM-Guided Reflection for Time Series Forecasting

Think-Before-Speak: From Internal Evaluation to Public Expression in Multi-Agent Social Simulation

Bridging the Last Mile of Time Series Forecasting with LLM Agents

An interpretable and trustworthy AI framework for large-scale longitudinal structure-pain association studies using data from the Osteoarthritis Initiative (OAI)

An Infectious Disease Spread Simulation Based on Large Language Model Decision Making

Characterizing initial human-AI proof formalization workflows

Self-Commitment Latency: A Reward-Free Probe for Prompted Implicit Hacking

Distilling Answer-Set Programming Rules from LLMs for Neurosymbolic Visual Question Answering

Agentic Molecular Recovery via Molecule-Aware Exploration

Multi-ResNets for Subspace Preconditioning in Constrained Optimization

WorldFly: A World-Model-Based Vision-Language-Action Model for UAV Navigation

Answer Presence Drives RAG Rewriting Gains

Parthenon Law: A Self-Evolving Legal-Agent Framework

A formal definition and meta-model for a machine theory of mind

Proof-Refactor: Refactoring Generated Formal Proofs into Modular Artifacts

The DeepSpeak-Agentic Dataset

Uncertainty Aware Functional Behavior Prediction and Material Fatigue Assessment for Circular Factory

Toward Pre-Deployment Assurance for Enterprise AI Agents: Ontology-Grounded Simulation and Trust Certification

When AI Says It Feels

Retry Policy Gradients in Continuous Action Spaces

BiNSGPS: Geometry Problem Solving via Bidirectional Neuro-Symbolic Interaction

GTBench: A Curriculum-Grounded Benchmark for Evaluating LLMs as Mathematical Research Assistants in Graph Theory

Beyond Vector Similarity: A Structural Analysis of Graph-Augmented Retrieval for Industrial Knowledge Graphs

SubtleMemory: A Benchmark for Fine-Grained Relational Memory Discrimination in Long-Horizon AI Agents

Uncertainty-Aware Clarification in LLM Agents with Information Gain

MCP-Persona: Benchmarking LLM Agents on Real-World Personal Applications via Environment Simulation

RASER: Recoverability-Aware Selective Escalation Router for Multi-Hop Question Answering

Evaluating Agentic Configuration Repair for Computer Networks

Perceive Before Reasoning: A Pre-Reasoning Perception Framework for Efficient and Reliable Proactive Mobile Agents

RelGT-AC: A Relational Graph Transformer for Autocomplete Tasks in Relational Databases

TokenMizer: Graph-Structured Session Memory for Long-Horizon LLM Context Management

GITCO: Gated Inference-Time Context Optimization in TSFMs