Knowledge catalogue
Paper linky - Context Language Models The central idea of the paper is incredibly simple. Give a model the ability to edit its context on-the-go like a file has major benefits on task performance, con
arXiv:2512.21439v2 Announce Type: replace-cross Abstract: A key question in current AI alignment research is how to make AI algorithms learn moral values. Because human morality is highly context-depe
Great overview of context compression in LLM Agents And one interesting, unexpected finding. If your compaction policy is tuned to cut tokens, it may be making your agent run slower. Great study from
arXiv:2610.02404v1 Announce Type: cross 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 simpl
arXiv:2609.33166v1 Announce Type: new Abstract: In-context reinforcement learning (ICRL) enables large language model agents to adapt to new environments using their interaction history without updati
arXiv:2609.34781v1 Announce Type: new Abstract: Vision-language models (VLMs) can read text in natural scenes, but their predictions may be influenced by the surrounding context. When the printed text
arXiv:2609.05761v1 Announce Type: new Abstract: Visual geolocation benchmarks typically ask a model where an image was captured without accounting for the location context that users often provide. We
arXiv:2507.06415v3 Announce Type: replace Abstract: Long-context reasoning requires accurately identifying relevant information in extensive, noisy input contexts. In this work, we propose PERK (Param
arXiv:2608.29897v1 Announce Type: new Abstract: Long-horizon agents need a context manager to compress growing interaction histories into a bounded working context, via passive strategies or active st
tldr: went from 16~ t/s to 27~ t/s generation. got my usable context up from 220k to the full 262k without sacrificing anything. prefill also increased from 376 to 573 command I ended up with, fwiw: l
arXiv:2608.05237v1 Announce Type: cross Abstract: Current few-step autoregressive video diffusion models depend on previous fully denoised clean frames as context for all denoising steps of the curren
arXiv:2605.10544v1 Announce Type: new Abstract: Long-context adaptation is often viewed as window scaling, but this misses a token-level supervision mismatch: in packed training with document masking,
arXiv:2604.17535v1 Announce Type: new Abstract: Extending the effective context length of large language models (LLMs) remains a central challenge for real-world applications. While recent post-traini
arXiv:2602.22175v2 Announce Type: replace Abstract: Understanding and reasoning over long contexts is a crucial capability for language models (LMs). Although recent models support increasingly long c
arXiv:2610.07559v1 Announce Type: new Abstract: Recent progress in tabular foundation models suggests that training on synthetic tasks can substantially improve in-context learning capabilities, with
arXiv:2610.07863v1 Announce Type: cross Abstract: Long-horizon LLM agents act on an append-only interaction history that is re-sent to the model at every step, so the context and its cost grow with st
arXiv:2610.08463v1 Announce Type: new Abstract: Long-context inference and Retrieval-Augmented Generation (RAG) handle evidence selection at vastly different scales, from a single long prompt to an en
arXiv:2609.37725v1 Announce Type: new Abstract: We introduce Context Language Models (CLMs), language models that natively manage their own context. We implement this by treating the context as a file
arXiv:2609.37791v1 Announce Type: new Abstract: Every day, people continuously infer situational context and adjust the way they understand and remember the world. Context, signaled by the prefrontal
arXiv:2609.26976v1 Announce Type: new Abstract: Learned context planning selects evidence atoms before an answer model reasons over them. We test whether this learned selection improves long-context m
arXiv:2609.22101v1 Announce Type: new Abstract: Large language models can process increasingly long prompts, yet their ability to locate and use decisive evidence may degrade as irrelevant or confusab
https://preview.redd.it/nulsv53o8vqh1.png?width=4500&format=png&auto=webp&s=74765dbd409f4c221640f9f6000a685f6fdbb242 Spent weekend benchmarking the Splash engine (by Incoai) and extending its architec
Jörg Schad is the VP of Engineering at @pinecone. He joins @kbal11 to discuss moving beyond RAG with precomputed context, context artifacts, semantic layers, and AI retrieval. @joerg_schad https://sof
arXiv:2608.15536v1 Announce Type: new Abstract: In value-based argumentation, an audience's ordering of values decides which attacks succeed as defeats. In many settings the deciding factor is not the
arXiv:2608.12218v1 Announce Type: cross Abstract: Large language models are increasingly trained and deployed with long contexts that span documents, code repositories, and interaction histories. This
arXiv:2608.10296v1 Announce Type: new Abstract: One might imagine that architectural variations within the dense transformer paradigm have a limited effect on accuracy. However, we demonstrate that th
https://preview.redd.it/xxjh11f38jih1.png?width=1852&format=png&auto=webp&s=76850ed51e29a8bc86c2ca718d4320075eed4363 Just wanted to share a user report that I found to be very interesting. Some person
Introducing Qwen-Audio-3.0-ASR-Flash: More context-aware. Stronger domain-term recognition. 🚀Our latest ASR model upgrades: • Context consistency • Domain-term recognition • Custom hotwords • Speech p
arXiv:2507.04221v3 Announce Type: replace-cross Abstract: We introduce Context Tuning, a simple and effective method to significantly enhance few-shot adaptation of large language models (LLMs) withou
you can now build RLMs with Deep Agents! the more context agents accumulate, the worse they perform, a phenomenon called context rot. RLMs, proposed by @a1zhang from MIT, help: instead of working mode
We trained language models that compress massive contexts into tiny latent representations. Latent Context Language Models (LCLMs) outperform existing KV cache compression methods on the latency/accur
Cursor can now show your agent's context usage as an interactive report in a canvas. The context explorer breaks down where tokens go across the system prompt, tool definitions, rules, skills, and mor
100% agree on the Context Hub. Developers constantly tweak their approaches to manage context in their prompts with each new model and tool suite release. I would even say that the core problem we fac
looks like new Pareto frontiers across everything: - Context: 400K context in Codex and a 1M in API - API Pricing: 5/m input and 30/m output tokens. - Codex improved its own inference speed 20% lol -
You can also set your autocompact threshold yourself and effectively lower your context window if you'd prefer. For example, 400k context is a good compromise: CLAUDE_CODE_AUTO_COMPACT_WINDOW=400000 c
deepagents now supports structured output for subagents! an under appreciated piece of context engineering is figuring out what context is passed back from subagents to the main agent. now you can def
arXiv:2610.11152v1 Announce Type: cross Abstract: LLM agents increasingly improve at inference time by accumulating experience in context rather than by updating parameters. This process is often desc
arXiv:2609.31430v1 Announce Type: new Abstract: Tool observations dominate the context of software-engineering agents, making long interaction histories costly to maintain. Existing context compressio
arXiv:2609.31382v1 Announce Type: cross Abstract: Long-context understanding requires large language models (LLMs) to reason over lengthy documents, conversations, and code, yet task-relevant evidence
arXiv:2609.18680v1 Announce Type: new Abstract: Contextual ASR can benefit from semantic cues or from target words explicitly provided in the context. We introduce HearInContext, a Mandarin--English b
arXiv:2604.07487v2 Announce Type: replace Abstract: Large language model agents rely on effective model context to obtain task-relevant information for decision-making. Many existing context engineeri
Interesting paper from Tencent. Tencent trains an agent to manage its own working context, and assigns credit at the level of individual context edits. Long-horizon tasks force a model to retrieve, in
arXiv:2512.15206v3 Announce Type: replace Abstract: A key bottleneck toward scalable IoT sensing is efficiently adapting trained AI models to new deployment conditions. Context shifts, such as changes
arXiv:2608.21690v1 Announce Type: new Abstract: LLM agents increasingly take on long-running tasks whose history grows far beyond a single model context window. Existing approaches compress earlier in
Graph: A cumulative metric of Speed x Context Size - the higher the dot - the better. Helpful for looking for the most balanced solution. The research relies on DFlash2 Q2 work by AnalogAlok: https://
arXiv:2603.06505v2 Announce Type: replace Abstract: Automatic speech recognition (ASR) has benefited from advances in pretrained speech and language models, yet most systems remain constrained to mono
arXiv:2607.29553v1 Announce Type: new Abstract: Organizations increasingly define operational metrics in structured, machine-readable formats to monitor systems, processes, and compliance. These metri
arXiv:2511.04249v2 Announce Type: replace Abstract: Sim-to-real transfer remains a major challenge in reinforcement learning (RL) for robotics, as policies trained in simulation often fail to generali
arXiv:2607.22575v1 Announce Type: new Abstract: Human episodic memory supports the retrieval of experiences that unfold over extended timescales, yet the computational mechanisms underlying this abili
arXiv:2606.10209v1 Announce Type: new Abstract: Large language models deployed as autonomous agents for enterprise workflows face a key challenge: verbose tool responses from enterprise systems can ca
arXiv:2605.30842v1 Announce Type: new Abstract: Context management enables agentic models to solve long-horizon tasks through iterative summarization of previous interaction histories. However, this p
arXiv:2605.25354v1 Announce Type: new Abstract: While LLMs excel at reasoning over prompts using static pretrained knowledge, they struggle significantly with context learning-the ability to dynamical
arXiv:2604.27043v1 Announce Type: new Abstract: Today's AI assistants such as OpenClaw are designed to handle context effectively, making context learning an increasingly important capability for mode
arXiv:2604.23277v1 Announce Type: cross Abstract: Long-context large language models remain computationally expensive to run and often fail to reliably process very long inputs, which makes context co
arXiv:2604.11462v1 Announce Type: new Abstract: Large Language Models (LLMs) struggle with long-horizon tasks due to the 'context bottleneck' and the 'lost-in-the-middle' phenomenon, where accumulated
arXiv:2604.07320v1 Announce Type: cross Abstract: Low-resource languages pose a challenge for machine translation with large language models (LLMs), which require large amounts of training data. One p
arXiv:2609.38379v1 Announce Type: new Abstract: Large language models (LLMs) are frequently updated for various use cases, where filtering out misaligned training samples is a common practice for prev
arXiv:2609.13141v1 Announce Type: new Abstract: Post-training attention sparsification reduces the quadratic cumulative attention cost of pretrained Transformers by selecting a small set of context un
I can't stand kv cache quantization. Even at q8_0, I can feel the difference. But realistically, when running Qwen3.8-27B-UD-Q4_K_XL on my 32 GB GPU, I only have room for ~170k tokens (with mtp and mm
Hello, I'm a bit obsessed with cache management on local LLMs. For the last few days I've been working on cache management on vLLM with my 2x DGX Spark and DeepSeek v4 Flash 0731. I felt something was