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: Coding · clear
Coding
11 papers
ZeroCoder: Can LLMs Improve Code Generation Without Ground-Truth Supervision?
2026-04-09 · arxiv
CodingSmall ModelRlvr
Awakening the Sleeping Agent: Lean-Specific Agentic Data Reactivates General Tool Use in Goedel Prover
2026-04-09 · arxiv
CodingFormal MathModel Release
ORACLE-SWE: Quantifying the Contribution of Oracle Information Signals on SWE Agents
2026-04-09 · arxiv
CodingSwe Bench
CODESTRUCT: Code Agents over Structured Action Spaces
2026-04-07 · arxiv
Coding
InCoder-32B-Thinking: Industrial Code World Model for Thinking
2026-04-03 · arxiv
Coding
From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents
2026-04-02 · arxiv
Coding
Yet Even Less Is Even Better For Agentic, Reasoning, and Coding LLMs
2026-04-01 · arxiv
Coding
KAT-Coder-V2 Technical Report
2026-03-29 · arxiv
Coding
ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code
2026-03-06 · arxiv
Coding
Qwen3-Coder-Next Technical Report
2026-02-28 · arxiv
Coding
SWE-Protege: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering Agents
2026-02-25 · arxiv
Coding