arXiv Machine Learning
PERK: Long-Context Reasoning as Test-Time Learning
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jun 4
Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning
arXiv:2505. 17315v2 Announce Type: replace Abstract: Recent language models exhibit strong reasoning capabilities, yet the influence of long-context capacity on reasoning remains underexplored.
arXiv AI
Jul 23
LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning
arXiv:2607. 19358v1 Announce Type: new Abstract: Recent advances in long chain-of-thought reasoning models such as DeepSeek-R1 have led to increasingly longer inference context lengths under the test-time scaling paradigm.
arXiv AI
Jul 3
ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
arXiv:2607. 02509v1 Announce Type: new Abstract: Understanding and reasoning over long contexts has become a key requirement for deploying large language models (LLMs) in realistic applications.
arXiv AI
Jul 13
Self-Guided Test-Time Training for Long-Context LLMs
arXiv:2607. 09415v1 Announce Type: cross Abstract: Long-context processing has become increasingly important for large language models (LLMs), but simply extending the context window does not guarantee effective utilization of long inputs.
arXiv Computation and Language
Sep 1
Randomized YaRN Improves Length Generalization for Long-Context Reasoning
Randomized YaRN is a training method that enhances length generalization for large language models by combining YaRN-based positional extrapolation with randomized positional encoding and a length curriculum. During training on short-context data, tokens receive YaRN positional encodings sampled from a larger position range, exposing the model to out-of-distribution positional representations. Evaluated on BABILong, Multi-Round Coreference Resolution, and LongBench v2, Randomized YaRN consistently improves reasoning performance on context lengths from 16K to 128K, outperforming standard fine‑tuning especially at far out‑of‑distribution lengths.
arXiv Machine Learning
Aug 4
Learning What to Remember: Test-Time Training via Context Distillation
arXiv:2608. 01672v1 Announce Type: cross Abstract: Effective long-context modeling is not merely about retaining more of the past, but about preserving the information that may prove relevant later.