Knowledge catalogue
📹 How to manage context the right way with LangSmith Context Hub Context Hub gives your team and your agent a shared place to store, edit, version, and retrieve context from It can be used for skills,
We launched Context Hub as a way to manage skills, AGENTS.md files, and other context files an agent might need You can easily use it as a virtual filesystem in deepagents See this video for more info
I've been experimenting with running larger models locally with Ollama, mainly because I'm interested in using them for agentic coding. I kept seeing benchmarks expressed as something like: 40 tokens/
Harrison Chase, co-founder of LangChain, endorsed the perspective that memory in AI agents is fundamentally a form of context, emphasizing that effective context management is the core requirement for
arXiv:2610.06679v1 Announce Type: new Abstract: Tabular foundation models perform in-context learning (ICL) by conditioning predictions on labeled training examples provided as context. Unlike traditi
Context compression is a huge bottleneck for long-running agents. This work finds that context compression hurts long-horizon agents at a few specific points. They propose PAIR, which replays the agen
arXiv:2610.06651v1 Announce Type: new Abstract: Methods for generalization in model-based reinforcement learning typically assume that an agent cannot recover the latent context governing the environm
arXiv:2609.00759v1 Announce Type: new Abstract: Large language models (LLMs) increasingly handle in-context learning (ICL) tasks where a long, novel context defines the rules, knowledge, and output sc
arXiv:2605.15721v1 Announce Type: new Abstract: Large Language Models (LLMs) are highly sensitive to their input contexts, motivating the development of automated context engineering. However, existin
arXiv:2606.06203v1 Announce Type: new Abstract: Input length and the position of relevant information are widely cited as the primary causes of degraded LLM long-context performance. Here, we study le
arXiv:2509.21361v2 Announce Type: replace-cross Abstract: Large language model (LLM) providers boast big numbers for maximum context window sizes. To test the real world use of context windows, we 1)
arXiv:2604.01601v2 Announce Type: replace Abstract: In-context fine-tuning (IC-Train), training an LLM with labeled examples in-context, is increasingly used in place of standard fine-tuning for domai
arXiv:2604.16686v1 Announce Type: new Abstract: Large language models (LLMs) can answer questions and summarize documents when conditioned on external contexts (e.g., retrieved evidence), yet context
arXiv:2510.11288v4 Announce Type: replace Abstract: Recent work has shown that narrow finetuning can produce broadly misaligned LLMs, a phenomenon termed emergent misalignment (EM). While concerning,
arXiv:2608.27756v1 Announce Type: new Abstract: Determining whether large language models derive answers from context or prior knowledge remains a fundamental challenge. Self-contained linguistic olym
This post was made with AI. I tried to remove as much slop as possible and keep it straight to the point to save your time as I know how annoying AI slop posts can be, but I still wanted to retain all
arXiv:2608.05141v1 Announce Type: new Abstract: Context lengths of language models (LMs) have dramatically increased, driven by the demands for in-context learning, self-improvement, and long-horizon
arXiv:2605.13831v1 Announce Type: new Abstract: Long-context modeling is becoming a core capability of modern large vision-language models (LVLMs), enabling sustained context management across long-do
Model. Harness. Context. The 3 main components of agents. As you build more agents, context increasingly lives AGENTS.md, skills, policies, examples, + generated research files. Context needs its own
arXiv:2511.03475v4 Announce Type: replace Abstract: AI applications increasingly depend on long-context inference, where LLMs consume substantial context to support stronger reasoning. Common examples
arXiv:2604.14339v1 Announce Type: new Abstract: Large language models (LLMs) increasingly operate in settings that require reliable long-context understanding, such as retrieval-augmented generation a
arXiv:2603.18446v2 Announce Type: replace Abstract: Long-context inference remains challenging for large language models due to attention dilution and out-of-distribution degradation. Context selectio
arXiv:2606.30005v1 Announce Type: new Abstract: Long-horizon tool agents are bottlenecked by how their context grows toward the limits of the context window. Recent systems make context management age
arXiv:2605.19932v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly operate over long and recurring external contexts, like document corpora and code repositories. Across in
We've productionized query-aware compression for faster, cleaner, more-accurate search. Better context is better than more context. Our system cuts context tokens up to 70% while improving answer qual
arXiv:2604.27660v1 Announce Type: new Abstract: Many real-world tasks require language models (LMs) to reason over complex contexts that exceed their parametric knowledge. This calls for context learn
arXiv:2604.07121v1 Announce Type: cross Abstract: In the human-AI collaboration area, the context formed naturally through multi-turn interactions is typically flattened into a chronological sequence
arXiv:2508.13993v2 Announce Type: replace Abstract: Long-context modeling is critical for a wide range of real-world tasks, including long-context question answering, summarization, and complex reason
arXiv:2609.12686v1 Announce Type: cross Abstract: Large language models (LLMs) process long contexts, including long documents and lengthy conversations, but face token-level memory usage that increas
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. In this
arXiv:2505.19293v2 Announce Type: replace-cross Abstract: Long-context capability is considered one of the most important abilities of LLMs, as a truly long context-capable LLM enables users to effort
arXiv:2510.02629v3 Announce Type: replace Abstract: Context utilisation, the ability of Language Models (LMs) to incorporate relevant information from the provided context when generating responses, r
arXiv:2604.23371v1 Announce Type: new Abstract: This paper investigates context stickiness in in-context learning (ICL), a phenomenon where earlier examples in a prompt interfere with a transformer's
a big part of agent harnesses is how they interact with context memory is just context its therefor impossible to separate harness from memory - as @sarahwooders says, 'memory isn't a plugin (it's a h
I am trying out a few fine-tunes of Qwen 3.5 9B @ IQ4_XS @ 131K context and trying to go mostly local (free beats cheap, after all). However, it is much slower than at, say 16K context, even when I am
// Reusable Context Engineering // Context bloat quietly kills long-horizon runs, but you can fix it from the outside without fine-tuning the underlying agent. (bookmark this) Context management is us
arXiv:2602.06358v2 Announce Type: replace Abstract: We propose SHINE (Scalable Hyper In-context NEtwork), a scalable hypernetwork that can map diverse meaningful contexts into high-quality LoRA adapte
The Harness is a Context Manager on Behalf of the Model What happens when the context window fills up and who decides? This decision is external to the model - The Harness designer must have some opin
Great paper for the weekend ahead. Meta presents Context Language Models, which can natively manage their own context. Banger paper from Meta and colleagues. (bookmark it) They discuss benefits of giv
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 g
arXiv:2607.23809v1 Announce Type: new Abstract: Agentic tasks are inherently long-horizon and multi-turn, constantly accumulating context through interactions with the environment. Existing context co
Your agentic workflows are only as good as the context you feed them. In finance, that context is stuck inside your messiest documents: dense tables, footnoted adjustments, and the details buried in t
arXiv:2609.27603v1 Announce Type: cross Abstract: In-Context Learning (ICL) has become a cornerstone of modern LLM deployment. However, existing ICL post-training methods have a critical blind spot: t
arXiv:2609.05955v1 Announce Type: new Abstract: Tabular foundation models have become powerful graph learners. Systems such as G2T-FM and GraphPFN encode each node as a feature row and make prediction
This is the Qwen3.8-27B setup I actually use every day on one RTX 5090. I wanted to write it down with enough detail that another 5090 owner can reproduce it instead of guessing which memory knobs I u
arXiv:2606.11627v1 Announce Type: cross Abstract: Recent work has shown that on-policy distillation can internalize privileged context, such as system prompts or task hints, into a student model so th
Everyone talks about 1M context. The harder part is making 1M context actually usable. Serving MiniMax M3 required optimizing for long-context, multimodal, and agentic workloads simultaneously. Excite
arXiv:2606.01336v1 Announce Type: new Abstract: As real-world applications increasingly require processing inputs of 100k+ tokens, the gap between context length and inference efficiency has become a
Cursor 3.3 introduces a context usage breakdown feature that allows users to view detailed statistics about how their AI agent consumes context tokens. This diagnostic tool helps identify context-rela
I was unable to retrieve the specific X (Twitter) post at the URL provided, as the content is not accessible through search results. The tweet's text snippet ('memory is context, and context is wha...
arXiv:2610.07894v1 Announce Type: new Abstract: Large language models (LLMs) are expected to answer questions faithfully based on the provided context, abstaining when the context information is insuf
arXiv:2610.05281v2 Announce Type: replace Abstract: Modern agents increasingly ground their reasoning in observations returned by tools, such as file contents read from a workspace. However, the data
Nice paper discussing context trimming for agents. This is a hot topic at the moment, so it might be worth your time. Context trimming for agents is usually judged by how many tokens it removes. This
arXiv:2511.20011v3 Announce Type: replace-cross Abstract: Pedestrian crossing intention prediction is essential for autonomous vehicles to improve pedestrian safety and reduce traffic accidents. Howev
arXiv:2608.03297v1 Announce Type: new Abstract: A standard claim in the literature on retrieval-augmented and memory-augmented language models is that shorter context is better when the relevant infor
arXiv:2607.03660v1 Announce Type: cross Abstract: Modern sequence models have a striking capacity for in-context learning (ICL); they can perform new tasks based only on examples given in the prompt.
// The Efficiency Frontier in LLMs // (bookmark this one) How much are you overpaying for context you do not need? It turns out that context costs dominate production LLM bills, and the right strategy
arXiv:2605.17304v1 Announce Type: cross Abstract: LLM context is not just tokens; it is a set of commitments. Long-running conversations accumulate goals, constraints, decisions, preferences, tool res
arXiv:2502.14644v5 Announce Type: replace Abstract: Long context understanding remains challenging for large language models due to their limited context windows. This paper introduces Long Input Fine
arXiv:2604.09494v1 Announce Type: cross Abstract: We propose RecaLLM, a set of reasoning language models post-trained to make effective use of long-context information. In-context retrieval, which ide