Claims Browser

The book offers a guided, project-driven learning experience rather than a broad survey.

"Reading the book feels like following a guided technical build rather than a loose survey of AI topics."

Refinement methods can sometimes degrade answers, a common failure mode in reasoning models.

"The book also discusses common failure modes, including cases where refinement can make answers worse."

Self-consistency, self-refinement, Best-of-N, and training-based methods have cost and latency trade-offs that are important to understand.

"Readers see how self-consistency, self-refinement, Best-of-N, and training-based methods actually work, including their cost and latency trade-offs."

The book implements core reasoning methods from scratch rather than using black-box library calls.

"The book is especially useful because it implements the core methods from scratch rather than treating them as black-box library calls."

Knowledge graphs and LLMs can be used together to build AI systems using connected data.

""Knowledge Graphs and LLMs in Action: Build AI systems using connected data""

OpenAI aims to devote time to announcing math results from internal models only when they would meaningfully change people's understanding of the pace of AI progress.

"At @OpenAI we aim to devote time to finding and announcing math results from internal models only when they would meaningfully change people’s understanding of the pace of AI progress."

OpenAI's main focus is shipping great models so that everyone can use them to make discoveries of their own.

"Our main focus is shipping great models so everyone can use them to make discoveries of their own."

CritICL consistently outperforms standard in-context learning and achieves performance competitive with or superior to test-time scaling methods while requiring significantly fewer generations and lower token cost

"Experimental results show that CritICL consistently outperforms standard in-context learning and achieves performance competitive with or superior to test-time scaling methods, while requiring significantly fewer generations and lower token cost"

CritICL improves reasoning while maintaining high efficiency by leveraging failure modes from weaker models as guidance through critique-based in-context examples

"CritICL, a novel inference-time framework that improves reasoning while maintaining high efficiency. Our key insight is that LLM failure modes exhibit structured patterns across model scales within the same family. Instead of treating failures as undesirable outputs, CritICL leverages them as a source of guidance. Specifically, we utilize failure modes derived from weaker models and incorporate them into inference through critique-based in-context examples"

LLM failure modes exhibit structured patterns across model scales within the same family

"LLM failure modes exhibit structured patterns across model scales within the same family"

Recent advances in inference-time scaling have significantly improved the reasoning performance of large language models

"Recent advances in inference-time scaling have significantly improved the reasoning performance of large language models (LLMs)"

Rollouts that disagree with pseudo-labels are typically wrong regardless of whether the vote itself is correct

"rollouts that disagree with the pseudo-label are typically wrong regardless of whether the vote itself is correct"

Majority-vote pseudo-labels are fragile because an incorrect vote corrupts the teacher and misleads every token

"Replacing ground truth with majority-vote pseudo-labels is a natural alternative, yet it is fragile: an incorrect vote corrupts the teacher and misleads every token"

TTPO shows strong cross-task generalization capabilities

"shows strong cross-task generalization"

TTPO yields +25.2% to +36.4% improvement without thinking

"yields +25.2% to +36.4% without thinking"

TTPO raises Qwen3-1.7B model performance from 38.0% to 45.2% during test-time training

"raises Qwen3-1.7B from 38.0% to 45.2% in TTT"

Test-Time Policy Optimization (TTPO) can match label-supervised OPSD performance on five competition-level benchmarks without using any labels

"Without any labels, TTPO matches label-supervised OPSD on five competition-level benchmarks"

Recent post-training methods like RL and OPSD have driven rapid progress in mathematical reasoning for large language models

"Recent prominent post-training methods, such as Reinforcement Learning (RL) and On-Policy Self-Distillation (OPSD), have driven rapid progress in mathematical reasoning for large language models"

Traditional inference-time scaling methods rely on repeated generation or external verification, which is a limitation

"these methods typically rely on repeated generation or external verification"