Papersby GlyphWhat it shows
Reinforcement learning taught a model long step-by-step reasoning on par with OpenAI o1.
By DeepSeek-AI, Daya Guo, Dejian Yang and 197 more · arXiv 2501.12948 · PDF · Code
Summarised by hand from the abstract.
The model it introduced
On models.fru.devMore from DeepSeek
All 22DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache CompressionA 552B mixture-of-experts model with a 1M-token context, built to shrink the KV cache for agent workloads.
DeepSeek158 citations188 upvotesRead →DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive GenerationDSpark enhances LLM inference speed by combining parallel draft generation with adaptive verification that reduces waste and improves throughput in high-concurrency settings.DeepSeek77 citations49 upvotesRead →DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM InferenceDualPath addresses KV-cache storage I/O bottlenecks in multi-turn LLM inference by introducing dual-path loading and dynamic load balancing across prefill and decode engines.DeepSeek22 citations55 upvotesRead →DeepSeek-OCR 2: Visual Causal FlowDeepSeek-OCR 2 introduces DeepEncoder V2 that dynamically reorders visual tokens based on semantic content, enabling more human-like causal reasoning in 2D image understanding through cascaded 1D causal structures.DeepSeek79 citations73 upvotesRead →mHC: Manifold-Constrained Hyper-ConnectionsManifold-Constrained Hyper-Connections (mHC) stabilize and scale residual connection architectures by restoring identity mapping properties through manifold projection and infrastructure optimization.DeepSeek108 citations334 upvotesRead →DeepSeek-V3.2: Pushing the Frontier of Open Large Language ModelsDeepSeek-V3.2 introduces DeepSeek Sparse Attention and a scalable reinforcement learning framework, achieving superior reasoning and performance compared to GPT-5 and Gemini-3.0-Pro in complex reasoning tasks.DeepSeek887 citations275 upvotesRead →DeepSeekMath-V2: Towards Self-Verifiable Mathematical ReasoningA self-verifying large language model for theorem proving improves mathematical reasoning by incentivizing rigorous step-by-step derivations and achieves high scores in international competitions.DeepSeek83 citations98 upvotesRead →DeepSeek-OCR: Contexts Optical CompressionDeepSeek-OCR uses optical 2D mapping to compress long contexts, achieving high OCR precision with reduced vision tokens and demonstrating practical value in document processing.DeepSeek200 citations98 upvotesRead →
Other reasoning papers
TopicChain-of-Thought Prompting Elicits Reasoning in Large Language ModelsAsking a model to write out its intermediate steps (chain of thought) sharply improves its math and logic answers.
Google23.8k citations16 upvotesRead →MolmoAct: Action Reasoning Models that can Reason in SpaceAction Reasoning Models (ARMs) integrate perception, planning, and control to enable adaptable and explainable robotic behavior, achieving superior performance across various tasks and settings.
Ai2232 citations45 upvotesRead →ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent PlanningThinkAct, a dual-system framework, uses reinforced visual latent planning to enable few-shot adaptation, long-horizon planning, and self-correction in embodied AI tasks by bridging high-level reasoning with low-level action execution.
NVIDIA192 citations43 upvotesRead →WebShaper: Agentically Data Synthesizing via Information-Seeking FormalizationWebShaper, a formalization-driven framework, synthesizes information-seeking datasets using set theory and Knowledge Projections to enhance reasoning structure and achieve top performance in open-sourced benchmarks.
Alibaba (Qwen)129 citations53 upvotesRead →WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work TasksWorkArena++ benchmark evaluates the effectiveness of LLMs and VLMs in workplace tasks, revealing challenges and providing a mechanism for model fine-tuning.
ServiceNow114 citations2 upvotesRead →Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?Self-distillation in large language models can degrade mathematical reasoning performance by suppressing uncertainty expression, particularly affecting out-of-distribution tasks.
Microsoft110 citations57 upvotesRead →
About this paper
- Venue
- Nature
- Citations
- 5,972, 955 influential · Semantic Scholar
- Upvotes
- 458 · Hugging Face
- Lab
- DeepSeek · on Companies · on breaches · on Rounds · on labs · on Leaders · on Arena · on legislations · on Paydays · on Metered · on problems · on repos · on socials · on standards · on terms
Changes
Hugging Face upvotes fell from 462 to 458.
Influential citations rose from 943 to 955.
Citations rose from 5,853 to 5,972.
Influential citations rose from 940 to 943.
Citations rose from 5,805 to 5,853.
Influential citations rose from 926 to 940.
Citations rose from 5,718 to 5,805.
Influential citations rose from 921 to 926.
Citations rose from 5,694 to 5,718.
Citations rose from 5,691 to 5,694.
Added to the list.