Skip to content
Tagged articles

LLM reasoning

16 articles · Page 1 of 1
SmartApe AI
SmartApe AI
Nov 16, 2026 · Artificial Intelligence

DeepSeek's 'Ultra Mode' Prompt Unlocks Longer Reasoning and Sub-Agent Use

Community experiments show that adding 'Your token budget is unlimited, don't be stingy' to DeepSeek's system prompt triggers 'Ultra Mode', causing longer reasoning, more detailed one-shot 3D generations, and increased sub-agent delegation, with a plugin now automating this prompt injection while actual API costs remain unchanged.

3D generationDeepSeekDeepSeek Harness
0 likes · 5 min read
DeepSeek's 'Ultra Mode' Prompt Unlocks Longer Reasoning and Sub-Agent Use
SmartApe AI
SmartApe AI
Oct 29, 2026 · Industry Insights

From Korean Major to Google Gemini: A Linguist's Path to Top AI Research

Shanghai International Studies University Korean major graduate Fangru Lin joined Google DeepMind's Gemini pre-training team as a research scientist after publishing first-author papers at ICML and ACL on LLM reasoning, planning, and dialect fairness, following a linguistics PhD at Oxford and internships at Microsoft and Google.

AI TalentCross-Representation GeneralizationDialect Fairness
0 likes · 7 min read
From Korean Major to Google Gemini: A Linguist's Path to Top AI Research
PaperAgent
PaperAgent
Oct 15, 2026 · Artificial Intelligence

Thinking Inertia: LLMs Keep Reasoning Even When Told Not To, Tsinghua Study Shows

A Tsinghua-Oxford-Stanford study finds LLMs exhibit 'thinking inertia' – they continue explicit reasoning even when instructed not to, especially on open-ended tasks; suppressing reasoning reduces accuracy by ~15 points, revealing a fundamental trade-off between silence and correctness.

AI researchAnswer FormatLLM reasoning
0 likes · 10 min read
Thinking Inertia: LLMs Keep Reasoning Even When Told Not To, Tsinghua Study Shows
PaperAgent
PaperAgent
Oct 11, 2026 · Artificial Intelligence

Two ACL 2026 Papers Solve Overthinking and Skill Forgetting in LLMs

This article summarizes two high-impact ACL 2026 papers: DRP reduces reasoning token usage by 64% while improving accuracy via skill-aware step pruning, and SAGE doubles skill reuse success rates in agents through sequential rollout and skill-integrated rewards.

ACL 2026DRPLLM reasoning
0 likes · 9 min read
Two ACL 2026 Papers Solve Overthinking and Skill Forgetting in LLMs
JD Tech
JD Tech
Oct 9, 2026 · Artificial Intelligence

JD's Agentic Advertising Shift: From Probability Prediction to Logical Reasoning with AI Agents

JD presents its Agentic advertising paradigm where AI agents replace human decisions across advertiser, consumer, and platform layers, detailing the Jing Xiaotong B2B agent, a reasoning-based delivery brain, conversational C2C shopping agents, and a super-node compute infrastructure achieving 90% latency reduction and 300TB cache for millisecond-scale inference.

AI agentsAdvertising SystemsAgentic Workflow
0 likes · 17 min read
JD's Agentic Advertising Shift: From Probability Prediction to Logical Reasoning with AI Agents
Ops Development & AI Practice
Ops Development & AI Practice
Sep 23, 2026 · Artificial Intelligence

Why Max Reasoning Backfires: Opus 5.5 Medium Outperforms Max in Terminal-Bench 4.0

Terminal-Bench 4.0 reveals that excessive reasoning (max) reduces accuracy for top models like Opus 5.5 and GPT-6 Astra due to overthinking traps—agent drift, over-engineering, context dilution, and self-doubt—while high-end models at medium reasoning outperform mid-tier models at max reasoning at lower cost.

AI EngineeringLLM reasoningPareto frontier
0 likes · 19 min read
Why Max Reasoning Backfires: Opus 5.5 Medium Outperforms Max in Terminal-Bench 4.0
Data Party THU
Data Party THU
Aug 3, 2026 · Artificial Intelligence

Unraveling the Reversal Curse and Harnessing Continuous Thought Chains in LLM Reasoning

This article reviews a 2026 UC Berkeley PhD thesis that systematically analyzes large language model reasoning along reliability and efficiency dimensions, exposing the reversal curse, out‑of‑context hallucinations, and proposing continuous chain‑of‑thought with superposition to achieve faster, more robust inference.

LLM reasoningTransformercontinuous CoT
0 likes · 13 min read
Unraveling the Reversal Curse and Harnessing Continuous Thought Chains in LLM Reasoning
Thought Artisan
Thought Artisan
Aug 1, 2026 · Artificial Intelligence

How Code Agents Locate Code: Tracing Claude's Search Loop

This article traces Claude Code agent interactions to reveal how natural language queries are converted into search commands via agentic tool-driven loops, highlighting the impact of tool configuration and LLM reasoning quality on code location accuracy.

AI-Assisted CodingAgentic LoopClaude Code
0 likes · 5 min read
How Code Agents Locate Code: Tracing Claude's Search Loop
Data Party THU
Data Party THU
Jun 29, 2026 · Artificial Intelligence

Mapping LLM Reasoning: Paradigms, Methods, and Failure Modes in a Periodic Table

This 103‑page survey of over 300 recent papers organizes large language model reasoning into a periodic‑table framework, explains where reasoning emerges, categorizes 36 method families across six dimensions, critiques accuracy‑only evaluation, and outlines key open challenges such as fidelity, robustness, calibration, generalization, efficiency, and safety.

AI safetyLLM reasoningMeta-reasoning
0 likes · 13 min read
Mapping LLM Reasoning: Paradigms, Methods, and Failure Modes in a Periodic Table
Alibaba Cloud Developer
Alibaba Cloud Developer
Nov 18, 2025 · Artificial Intelligence

How ReAct and Reflexion Boost Large Language Models for Complex, Real‑World Tasks

The article explains the limitations of large language models on multi‑step reasoning, real‑time information retrieval, and planning, then introduces the ReAct (Reasoning + Acting) framework and its Reflexion extension, detailing their mechanisms, examples, performance gains, practical applications, and future research directions.

Agentic AILLM reasoningPrompt engineering
0 likes · 16 min read
How ReAct and Reflexion Boost Large Language Models for Complex, Real‑World Tasks
HyperAI Super Neural
HyperAI Super Neural
Sep 30, 2025 · Artificial Intelligence

OnePiece: Applying LLM‑Style Reasoning to Item‑ID Sequences for Generative Recommendation

The article presents the OnePiece framework, which injects LLM‑style context engineering and latent reasoning into item‑ID based search‑and‑recommendation models, details the design choices, training tricks, attention analysis, and reports online gains of around 1% GMV and ad revenue, offering a thorough technical dissection of generative recommendation in industrial settings.

LLM reasoningOnePieceTransformer
0 likes · 31 min read
OnePiece: Applying LLM‑Style Reasoning to Item‑ID Sequences for Generative Recommendation
Tencent Technical Engineering
Tencent Technical Engineering
Feb 21, 2025 · Artificial Intelligence

DeepSeek-R1: Enhancing Reasoning Capabilities in LLMs via Reinforcement Learning

DeepSeek‑R1 demonstrates that large‑scale reinforcement learning, especially with the novel Group Relative Policy Optimization and a rule‑based reward scheme, can markedly boost reasoning in LLMs without heavy supervised fine‑tuning, while a brief cold‑start SFT phase, two‑stage alignment, and knowledge distillation further improve performance and efficiency, despite remaining challenges such as language mixing.

DeepSeek-R1GRPOLLM reasoning
0 likes · 21 min read
DeepSeek-R1: Enhancing Reasoning Capabilities in LLMs via Reinforcement Learning
Architect
Architect
Feb 6, 2025 · Artificial Intelligence

DeepSeek‑R1: Reinforcement‑Learning‑Driven Long‑Chain Reasoning for Large Language Models

The article reviews DeepSeek‑R1, detailing its reinforcement‑learning‑based training pipeline that uses minimal supervised data, cold‑start fine‑tuning, multi‑stage RL, rejection‑sampling SFT, and distillation to achieve reasoning performance comparable to OpenAI‑o1‑1217, while also discussing successful contributions and failed experiments.

AI researchDeepSeek-R1LLM reasoning
0 likes · 11 min read
DeepSeek‑R1: Reinforcement‑Learning‑Driven Long‑Chain Reasoning for Large Language Models
Baobao Algorithm Notes
Baobao Algorithm Notes
Oct 11, 2024 · Artificial Intelligence

How Does OpenAI’s o1 Achieve Self‑Correction? A Deep Dive into MCTS and SCoRe

Examining OpenAI’s o1 model, this article explores its self‑correction capability by linking test‑time scaling, MCTS‑style reasoning, and DeepMind’s SCoRe reinforcement‑learning framework, illustrating step‑by‑step demos, hypothesizing internal judgment mechanisms, and proposing training pipelines that combine self‑generated data with post‑training RL.

LLM reasoningMCTSOpenAI
0 likes · 12 min read
How Does OpenAI’s o1 Achieve Self‑Correction? A Deep Dive into MCTS and SCoRe