arXiv:2608. 03048v1 Announce Type: cross Abstract: Long-context reasoning remains a critical bottleneck for large language models, as recent recurrent-memory approaches face two inherent challenges: sequential chunk-wise updates can overwrite early critical evidence with later irrelevant content, and serial inter-chunk dependencies limit parallelism and cause latency to increase with context length.
By Dawei Liu, Haixu Song, Shuang Cheng, Shijie Wang, Haozheng Hou, Kaifeng Liu, Ermo Hua, Zhonghang Yuan, Zhijie Zhong, Yuchen Fan, Biqing Qi, Bowen Zhou
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.
By Yu Zhao, Zekun Zhang, Fan Jiang, Bo Zeng, Linlong Xu, Shimin Shan, Yu Liu, Longyue Wang, Weihua Luo
arXiv:2607. 02980v1 Announce Type: cross Abstract: Scaling modern large language models (LLMs) to long contexts is limited by the quadratic computation cost, and poor length extrapolation of dense attention.
By Xiang Hu, Xinyu Wei, Hao Gu, Minshen Zhang, Tian Liang, Huayang Li, Lei Zhu, Yan Wang, Sirui Han, Yushi Bai, Kewei Tu, Haitao Mi, Leo Liang
arXiv:2609.35831v1 Announce Type: new
Abstract: Modern large language models now support context windows of more than one million tokens, which has raised the question of whether retrieval-augmented...
By Isaac Olufadewa, Miracle Adesina, Ezekiel Oladejo, Owen Adeniyi, Fadare Fadekemi, Olamide Oso, Uthman Babatunde, Matthew Olawoyin
Long-context large language model (LLM) inference is increasingly constrained by the memory footprint and decoding cost of key-value (KV) caches, limiting sustainable deployment on resource-constrained hardware. Existing KV cache eviction methods typically apply heuristic token scoring over all heads in GQA-based LLMs.
arXiv:2606. 24467v1 Announce Type: new Abstract: Long-context large language model (LLM) inference is increasingly constrained by the memory footprint and decoding cost of key-value (KV) caches, limiting sustainable deployment on resource-constrained hardware.
By Xiaolin Lin, Jingcun Wang, Olga Kondrateva, Yiyu Shi, Bing Li, Grace Li Zhang
arXiv:2607. 08284v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated rapidly improving long-context capabilities, prompting a wave of benchmarks designed to evaluate them.
By Siddhartha Jain, Ameya Velingker
Large language models (LLMs) have demonstrated rapidly improving long-context capabilities, prompting a wave of benchmarks designed to evaluate them. However, existing long-context evaluations - from Needle-in-a-Haystack (NIAH) tests to more recent multi-hop reasoning and summarization tasks - predominantly measure average-case performance, and many are either saturated or lack robustness.
arXiv:2606. 09508v1 Announce Type: new Abstract: Existing sparse attention and KV cache compression methods for long-context LLM inference typically apply fixed sparsity patterns or uniform budgets across all attention heads, overlooking the substantial variation in attention behavior among heads and contexts.
By Zhanchao Xu, Haoyang Li, Qingfa Xiao, Fei Teng, Chen Jason Zhang, Lei Chen, Qing Li
arXiv:2610.08463v1 Announce Type: cross
Abstract: Long-context inference and Retrieval-Augmented Generation (RAG) handle evidence selection at vastly different scales, from a single long prompt to an...
By Edan Kinderman, Elad Hoffer, Yochai Blau, Brian Chmiel, Ron Banner, Daniel Soudry, Boris Ginsburg
Large language models (LLMs) often process entire input contexts even when only a small portion is needed to answer a query. The authors introduce dynamic context cutoff, a technique that lets LLMs self‑terminate processing once they have gathered enough task‑relevant information. By analyzing model internals, they find that certain attention heads encode latent sufficiency signals that can be detected with lightweight classifiers, enabling efficient context handling. Experiments on six QA datasets with LLaMA, Qwen, and Mistral models (1B–70B) show a 3.4 % accuracy gain and a 1.33× reduction in token usage, outperforming other context‑efficiency methods at similar token reductions. The study also notes that larger models can intrinsically assess sufficiency through prompting, while smaller models need explicit probing.
By Roy Xie, Junlin Wang, Paul Rosu, Chunyuan Deng, Bolun Sun, Zihao Lin, Bhuwan Dhingra
arXiv:2607. 01792v1 Announce Type: cross Abstract: While decoder-only LLMs excel at a vast array of natural language tasks, it suffers from an asymmetric information flow induced by causal attention: later tokens are richer in contextual grounding than earlier ones.
By Andikawati P Widjaja, Yongjun Kim, Hyounghun Kim, Jaeho Lee