This work trains a model over the simplest possible harness: a tool to call itself with any specified prompt and a tool to read tokens in a range from the input context over a diverse synthetic dataset.
Abstract
We study long context language models. Instead of training long context natively, or designing a long context harness, we train a model over the simplest possible harness: a tool to call itself with any specified prompt and a tool to read tokens in a range from the input context. We finetune Qwen3.6-35B-A3B on a diverse synthetic dataset using this harness. With only 8,000 tokens of context, our small model is as strong as GPT-5.4 with 1M tokens of context on the OOLONG-synth benchmark when document length exceeds 40K tokens.
Context Language Models are introduced, language models that natively manage their own context and can be steered with natural-language instructions evolved through a standard skill-optimization loop, improving held-out accuracy by up to 35.9 points on a context-management task while reducing compute.
Ru-Lin Shao, Shannon Zejiang Shen, J. Yin et al.· 4 citations
As LLM agents operate over corpora of more than ten thousand tools, selecting the right tool for a complex multi-step user instruction becomes a central bottleneck. Tool descriptions cannot all fit in context, and relevance-based retrievers only rank tools without knowing which are actually needed. Recent work instead...
Zhao-Yi Zhou, Akshayaa Magesh, Jeongyeol Kwon et al.· 0 citations
This work attempts to make use of high-quality public documents with small perturbations and empirically finds that LLMs can successfully generate context-dependent reasoning traces and answers, which are then used to train a student model that substantially improves the performance on CL-bench.
Hao Wu, Yang Xiao, Yu-Song Sun et al.· 0 citations
Reinforcement learning (RL) is an effective way to strengthen the long-context reasoning of large language models (LLMs), but it needs training data that are long, diverse, challenging, and verifiable. Human annotation of such data is expensive, naturally occurring data are too scarce to sustain RL, and existing synthe...
This paper focuses on the problem of demonstration selection, which involves selecting a subset of examples for prepending to a query to a language model, and builds on state space models (SSMs), which require only linear inference time given the input.
Zi-Niu Zhang, Zhen-Shuo Zhang, Ruo-Xuan Xiong et al.· 0 citations
The Context Compilation Architecture (CCA), whose central novelty is a typed intermediate representation (IR) with fixed slots (rules.{must_do, must_not, conditional}, output_spec, available_tools, data_profile) into which any prose context is compiled once; executable verifiers and a violation-gated correction loop fo...
Jin-Hu Qi, Min-Da Hu, Wen-Tao Zhang et al.· 0 citations
Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
