Do Domain-specific Experts exist in MoE-based LLMs?

2026-04-07 · arxiv

QED-Nano: Teaching a Tiny Model to Prove Hard Theorems

2026-04-06 · arxiv

Search, Do not Guess: Teaching Small Language Models to Be Effective Search Agents

2026-04-06 · arxiv

Reinforcement Learning-based Knowledge Distillation with LLM-as-a-Judge

2026-04-03 · arxiv

S3: Stratified Scaling Search for Test-Time in Diffusion Language Models

2026-04-02 · arxiv

ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement

2026-04-02 · arxiv

Embarrassingly Simple Self-Distillation Improves Code Generation

2026-04-01 · arxiv

SARL: Label-Free Reinforcement Learning by Rewarding Reasoning Topology

2026-03-30 · arxiv

Do Post-Training Algorithms Actually Differ? A Controlled Study Across Model Scales Uncovers Scale-Dependent Ranking Inversions

2026-03-19 · arxiv

Beyond Test-Time Training: Learning to Reason via Hardware-Efficient Optimal Control

2026-03-10 · arxiv

DiSCTT: Consensus-Guided Self-Curriculum for Efficient Test-Time Adaptation in Reasoning

2026-03-05 · arxiv

Structured Distillation of Web Agent Capabilities Enables Generalization

2026-04-09 · arxiv

IntentScore: Intent-Conditioned Action Evaluation for Computer-Use Agents

2026-04-06 · arxiv

Beyond Fixed Tests: Repository-Level Issue Resolution as Coevolution of Code and Behavioral Constraints

2026-04-06 · arxiv

InfoSeeker: A Scalable Hierarchical Parallel Agent Framework for Web Information Seeking

2026-04-03 · arxiv

Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design

2026-03-30 · arxiv

Seed1.8 Model Card: Towards Generalized Real-World Agency

2026-03-21 · arxiv

WebNavigator: Global Web Navigation via Interaction Graph Retrieval

2026-03-20 · arxiv

A Subgoal-driven Framework for Improving Long-Horizon LLM Agents

2026-03-20 · arxiv

OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data

2026-03-16 · arxiv

Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents (GUI-Owl-1.5)

2026-02-15 · arxiv

OpAgent: Operator Agent for Web Navigation

2026-02-14 · arxiv

Agent Alpha: Tree Search Unifying Generation, Exploration and Evaluation for Computer-Use Agents

2026-02-03 · arxiv

ZeroCoder: Can LLMs Improve Code Generation Without Ground-Truth Supervision?

2026-04-09 · arxiv

Awakening the Sleeping Agent: Lean-Specific Agentic Data Reactivates General Tool Use in Goedel Prover

2026-04-09 · arxiv

ORACLE-SWE: Quantifying the Contribution of Oracle Information Signals on SWE Agents

2026-04-09 · arxiv

CODESTRUCT: Code Agents over Structured Action Spaces

2026-04-07 · arxiv

InCoder-32B-Thinking: Industrial Code World Model for Thinking

2026-04-03 · arxiv

From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents

2026-04-02 · arxiv

Yet Even Less Is Even Better For Agentic, Reasoning, and Coding LLMs

2026-04-01 · arxiv

KAT-Coder-V2 Technical Report

2026-03-29 · arxiv

ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code

2026-03-06 · arxiv

Qwen3-Coder-Next Technical Report

2026-02-28 · arxiv

SWE-Protege: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering Agents

2026-02-25 · arxiv

MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale

2026-04-06 · arxiv

CharTool: Tool-Integrated Visual Reasoning for Chart Understanding

2026-04-03 · arxiv

Q-Mask: Query-driven Causal Masks for Text Anchoring in OCR-Oriented Vision-Language Models

2026-03-31 · arxiv

Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Training

2026-03-25 · arxiv

Agentar-Fin-OCR

2026-03-11 · arxiv

Qianfan-OCR: A Unified End-to-End Model for Document Intelligence

2026-03-11 · arxiv

GLM-OCR Technical Report

2026-03-11 · arxiv

DocCogito: Aligning Layout Cognition and Step-Level Grounded Reasoning for Document Understanding

2026-03-08 · arxiv

FireRed-OCR Technical Report

2026-03-02 · arxiv

PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust Document Parsing

2026-01-29 · arxiv

MolmoWeb: Open Visual Web Agent and Open Data for the Open Web

2026-04-09 · arxiv

ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning

2026-04-07 · arxiv

Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation

2026-03-19 · arxiv

Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning

2026-01-15 · arxiv

MiMo-V2-Flash Technical Report

2026-01-06 · arxiv

Dead Weights, Live Signals: Feedforward Graphs of Frozen Language Models

2026-04-09 · arxiv

Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents

2026-04-08 · arxiv

Multi-objective Evolutionary Merging Enables Efficient Reasoning Models

2026-04-07 · arxiv

PRISM-MCTS: Learning from Reasoning Trajectories with Metacognitive Reflection

2026-04-06 · arxiv

Phi-4-reasoning-vision-15B Technical Report

2026-03-04 · arxiv

SUPERNOVA: Eliciting General Reasoning in LLMs with Reinforcement Learning on Natural Instructions

2026-04-09 · arxiv

Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution

2026-04-09 · arxiv

Apriel-1.5-OpenReasoner: RL Post-Training for General-Purpose and Efficient Reasoning

2026-04-02 · arxiv

ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence

2026-03-24 · arxiv

Vero: An Open RL Recipe for General Visual Reasoning

2026-04-06 · arxiv

Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders

2026-03-06 · arxiv

STEP3-VL-10B Technical Report

2026-01-14 · arxiv

KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluation

2026-04-09 · arxiv

Don't Act Blindly: Robust GUI Automation via Action-Effect Verification and Self-Correction

2026-04-07 · arxiv

Demystifying OPD: Length Inflation and Stabilization Strategies for Large Language Models

2026-04-09 · arxiv

Cross-Tokenizer LLM Distillation through a Byte-Level Interface

2026-04-08 · arxiv

Firebolt-VL: Efficient Vision-Language Understanding with Cross-Modality Modulation

2026-04-06 · arxiv

Empirical Recipes for Efficient and Compact Vision-Language Models

2026-03-17 · arxiv

TTVS: Boosting Self-Exploring Reinforcement Learning via Test-time Variational Synthesis

2026-04-09 · arxiv

SeLaR: Selective Latent Reasoning in Large Language Models

2026-04-09 · arxiv

MARS: Enabling Autoregressive Models Multi-Token Generation

2026-04-09 · arxiv

FLUX: Data Worth Training On

2026-03-14 · arxiv

DMax: Aggressive Parallel Decoding for dLLMs

2026-04-10 · arxiv

JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency

2026-04-03 · arxiv

Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts

2026-04-09 · arxiv

OmniDocBench Leaderboard Update (2026/03/31)

2026-03-31 · arxiv

SliderQuant: Accurate Post-Training Quantization for LLMs

2026-03-26 · arxiv

Self-Distilled RLVR

2026-04-06 · arxiv

Claude Mythos Preview System Card

2026-04-07 · arxiv

Gemma 4, Phi-4, and Qwen3: Accuracy-Efficiency Tradeoffs in Dense and MoE Reasoning Language Models

2026-04-08 · arxiv

When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoning

2026-04-09 · arxiv

OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks

2026-04-09 · arxiv