127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “reasoning”

19,026 results

Model Releases

Random Recursive Models

DGX agent

arXiv:2610.00541v1 Announce Type: cross Abstract: Recursive models create computational depth through parameter reuse, offering a parameter-efficient alternative to increasing model size. However, mos

model-releasesarxiv-cs-ai

2 Oct 2026

Model Releases

Retrospective Open-Vocabulary Memory for Long-Term Object Search

DGX agent

arXiv:2610.00330v1 Announce Type: cross Abstract: Long-term object search requires learning where objects usually appear from repeated but uneven observations of a changing environment. We formulate r

Search: “reasoning”

Random Recursive Models

Retrospective Open-Vocabulary Memory for Long-Term Object Search

Scalable Delphi: Large Language Models for Structured Risk Estimation

Science or Slop?: Benchmarking and Mitigating Scientific Slop in AI-Generated Papers

STATERA: Hidden Mass Estimation via Zero-Shot Sim-to-Real Kinematics using Frozen Temporal Tubelets

Token Communication-Assisted Collaborative Embodied Artificial Intelligence: Concepts, Framework, and Opportunities

Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes

Why GRPO Needs Normalization: A Local-Curvature Perspective on Adaptive Gradients

Adaptive-GEPA: Make Your Harness Fit Heterogeneous Requests

AssemblyWorld: Rethinking 3D Assembly with General-Purpose Agents

Automatic estimation of verbal fluency index in people with Motor Neuron Disease using ASR alignment and pause modelling

Breaking Babel: A Self-Evolving Multi-Agent System for Long-Form Subtitle Translation

Can an AI Agent Rediscover a Blaschke-Curve Invariant?

Candidate Retention for Abductive Learning

ChartDensity-Bench: Benchmarking MLLMs for Numerical Data Reconstruction under Visual Density

Cheap to Draw, Expensive to Trust: Certifying Test-Time Scaling Curves

Concept-Grounded Attention: A Controlled Evaluation of Graph-Injected Attention, Temporal Versioning, and Epistemic Status

Concurrent Semantic Search and Mission Execution for LTL Missions in Unknown Environments

Conditional Generation of Creative Chess Puzzles with Diffusion Models

Disentangling Self-Distillation: Measuring and Modeling Acquisition and Retention

EviRover: Reinforcing Agentic Perception Beyond a Glance

Examining Variation in How Guided AI Tutors Resolve Student Impasses

Inferring Causal Relations between Two Sequences of Events with Language Models

Lasting Effects of Abstract Pretraining Beyond Perplexity

LEAP: Learned Block-wise Evidence Retrieval for Long Audio-Video Perception

LexReward: A Taxonomy-Driven Reward Framework for Legal Language Models

LoopVL: Recurrent Visual Intelligence

Make Code as Policy Great Again: Frontier Agents Write, Call, and Evolve Robot Tools

MEMO: Multi-Level Entity-Aware Memory for Streaming Video Understanding

Multi-agent discussion gains less when dissent is withheld

Occlusion-Aware, Quasi-Static, Stability-Oriented Trajectory Planning on Uneven Terrain

OPSRD: On-Policy Self-Role Distillation

Over-Personalization Is a Decision Failure: Generation-Induced Apply Bias in LLMs

SceneJail: Exploiting Video Scenario Context to Jailbreak Multimodal LLMs

SEPAL: Separated Expert Pairs with Answer-Level Fusion for Reliable LLM Collaboration

Shared Weights, Selected Computations: How Looped Transformers Route What Each Loop Does

SimEX: Simulation-Integrated Robotics AutoResearch

StreamDecisionBench: Evaluating Decisions in Force on Evolving Language Streams

TACTIC: Temporal and Context-Aware LLM Tactical Planning for Roadside LiDAR Attacks

Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively?

Towards Better Exploration in Sequential Test-Time Scaling

Unlearning Deceptive Behaviors in LLMs with Contrastive Forget Sets

Where MLLMs Fail and Why: Causal Task Decomposition for Capability Failure Diagnosis

AdaptArena: Evaluating Test-Time Personalization of Web Agents

Adaptive Consistency Graph for Long-Horizon Agents

Backdoor in the Loop: Compromising Agentic Search via Malicious Retrievers

Beyond Symmetric Agents: Cognitive Diversity and Multi-Agent Debate in Small Language Models

Block Sparse Flash Attention