Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning
The paper presents a novel training framework called ProxyCoT aimed at improving long-context reasoning in large language models. It highlights the performance disparity between proxy contexts and full contexts in reasoning tasks. The proposed method demonstrates improved efficiency and generalization in reasoning capabilities across various datasets.
- ▪Large language models struggle with long-context tasks that require complex reasoning.
- ▪ProxyCoT transfers reasoning capabilities from short proxy contexts to full long contexts.
- ▪Experiments show that ProxyCoT outperforms strong baselines with reduced computational overhead.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.20201 |
| Publication time | Fri, 22 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-22T04:02:00.009Z |
| Last seen | 2026-05-22T04:02:00.009Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | 8ZXltRWgo_ug |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Computation and Language arXiv:2605.20201 (cs) [Submitted on 6 Apr 2026] Title:Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning Authors:Miao Li, Irina Saparina, Alexander Gurung, Mirella Lapata View a PDF of the paper titled Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning, by Miao Li and 3 other authors View PDF HTML (experimental) Abstract:Recent large language models support inputs of up to 10 million tokens, yet they perform poorly on long-context tasks that require complex reasoning. Such tasks can be solved using only a subset of the input -- a proxy context -- rather than the full sequence. Despite sharing the same underlying reasoning process, models exhibit a significant performance disparity between proxy and full contexts.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
