Home›Papers
Papers
Papers
Papers that changed AI, with a plain-language explainer for each.
Total 58 · Clear filters
- 2026
GLM-5: from Vibe Coding to Agentic Engineering
arXiv
Zhipu's GLM-5 report describes a 744-billion-parameter mixture-of-experts model built on sparse attention and asynchronous reinforcement learning, aimed at moving AI-assisted programming from vibe coding toward agentic engineering.
- 2026
Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
arXiv
Terminal-Bench 2.0 is a curated benchmark of 89 hard tasks carried out in computer terminal environments, built to measure how well AI agents handle realistic command-line work; frontier models and agents score below 65% on it.
- 2025
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
arXiv
The Gemini 2.5 technical report, submitted to arXiv on 7 July 2025, documents Google's Gemini 2.5 Pro and 2.5 Flash models: their reasoning, long-context video handling, and cost-versus-capability positioning.
- 2025
ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems
arXiv
A 2025 paper introducing ARC-AGI-2, a benchmark of input-output puzzle tasks built to measure abstract reasoning in frontier AI systems, with human testing as a baseline and a task set designed to give a more granular signal of progress.
- 2025
Qwen3 Technical Report
arXiv
The Qwen3 Technical Report presents Alibaba's Qwen3 family of dense and mixture-of-experts language models, which unify thinking and non-thinking modes, add a controllable thinking budget, and are released under the Apache 2.0 licence.
- 2025
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
arXiv
A 2025 paper proposing Absolute Zero, a reinforcement-learning paradigm in which one model writes its own code-reasoning tasks and then solves them, with a code executor as the only judge, reaching state of the art on coding and maths without external training data.
- 2025
s1: Simple test-time scaling
arXiv
A paper showing that a 32B model fine-tuned on 1,000 carefully chosen questions and run with a simple "budget forcing" trick can beat o1-preview on competition maths by up to 27%, with model, data and code released.
- 2025
Humanity's Last Exam (HLE)
arXiv
Humanity's Last Exam (HLE) is a 2,500-question, multi-modal benchmark spanning dozens of academic subjects, built by experts worldwide so that frontier language models can still be measured after saturating older tests.
- 2025
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
arXiv
The DeepSeek-R1 report described how a reasoning model was trained largely with reinforcement learning, rewarding correct answers, and reached performance comparable to OpenAI's o1 on math, code and reasoning benchmarks. Its weights were released openly.
- 2024
FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI
arXiv
FrontierMath is a benchmark of hundreds of original, unpublished mathematics problems written and vetted by expert mathematicians, introduced by Epoch AI to test advanced mathematical reasoning in AI. At release, state-of-the-art models solved under 2% of the problems.[^1][^2]
- 2024
FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision
arXiv
FlashAttention-3 is an attention algorithm for NVIDIA Hopper (H100) GPUs that reaches up to 75% utilization in FP16 and close to 1.2 PFLOPs/s in FP8, using asynchronous execution and low-precision techniques.
- 2024
MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
arXiv
MMLU-Pro is a 2024 benchmark that makes the widely used MMLU knowledge test harder: its questions are reasoning-focused and each has ten answer options instead of four.
- 2024
Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
ICML
Tri Dao and Albert Gu's paper introduces state space duality, a framework showing that structured state space models and attention variants are closely related, and uses it to derive Mamba-2, whose core layer runs 2 to 8 times faster than Mamba's.
- 2024
LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
arXiv
A benchmark for code LLMs that keeps collecting fresh contest problems from LeetCode, AtCoder and CodeForces, so that scores reflect ability rather than memorised test data, and that also tests code repair and execution reasoning.
- 2023
GAIA: a benchmark for General AI Assistants
arXiv
GAIA is a benchmark of real-world questions that are easy for humans but hard for AI assistants, testing reasoning, multimodality, web browsing, and tool use. It compares AI progress against average human performance.
- 2023
GPQA: A Graduate-Level Google-Proof Q&A Benchmark
arXiv
GPQA is a benchmark of 448 expert-written multiple-choice questions in biology, physics and chemistry, built so that skilled non-experts cannot look the answers up, and hard enough that the strongest GPT-4 baseline scored 39% while domain experts reached 65%.
- 2023
SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
arXiv
A benchmark of 2,294 real software engineering problems taken from GitHub issues and the pull requests that resolved them, in which a model must edit a codebase to fix an issue; on release the best model solved under 2% of them.
- 2023
FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
arXiv
FlashAttention-2 is a 2023 revision of the FlashAttention attention kernel that reorganizes work across GPU thread blocks and warps, roughly doubling speed and reaching up to 73% of the A100's theoretical peak throughput.
- 2023
QLoRA: Efficient Finetuning of Quantized LLMs
arXiv
QLoRA is a finetuning method that trains a 65B-parameter language model on a single 48GB GPU while matching full 16-bit finetuning quality, using 4-bit quantization, double quantization and paged optimizers.
- 2023
Sparks of Artificial General Intelligence: Early experiments with GPT-4
arXiv
A March 2023 paper by Microsoft researchers testing an early GPT-4, arguing it shows strikingly general, near-human performance across many domains and could be seen as an early but incomplete step toward AGI.