research
Papers
81 papers with benchmark results from arxiv, tagged by theme
Small Beats Big 11Agent 12Coding 11OCR 10Efficient 5Frontier 5Reasoning 4VLM 3Browser Agent 2Distillation 2Small VLM 2Test Time Compute 2Autoregressive 1Data Curation 1Diffusion LLM 1Model Release 1MOE 1OCR Document 1Quantization 1Rlvr 1Safety Evaluation 1Small Models 1Tool Use 1Vision Language 1
Filtering by: Frontier · clear
Frontier
5 papers
Dead Weights, Live Signals: Feedforward Graphs of Frozen Language Models
2026-04-09 · arxiv
FrontierModel CombinationSmall Model
Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents
2026-04-08 · arxiv
FrontierAgentReasoning
Multi-objective Evolutionary Merging Enables Efficient Reasoning Models
2026-04-07 · arxiv
FrontierReasoningModel Merging
PRISM-MCTS: Learning from Reasoning Trajectories with Metacognitive Reflection
2026-04-06 · arxiv
FrontierReasoningSearch
Phi-4-reasoning-vision-15B Technical Report
2026-03-04 · arxiv
FrontierNew ModelVLMSmall Model