Search: “context”

arXiv:2608.15962v1 Announce Type: new Abstract: Long-context reasoning remains computationally expensive for large language models due to the quadratic complexity of attention over text tokens. Visual

arXiv:2608.16370v1 Announce Type: new Abstract: Task completion is the standard metric for evaluating context compression, yet it is incomplete: compression can increase an agent's interaction cost by

arXiv:2608.14528v1 Announce Type: new Abstract: This study investigates the methodological and theoretical properties of session handover in applications that use large language models. A task may con

arXiv:2608.12627v1 Announce Type: cross Abstract: Long-horizon egocentric memory transforms continuous first-person video and audio into a searchable record of past experiences. We demonstrate two bot

Qwen3.8-2.4T-A95B is live on Together AI. The Qwen team’s new open-weight MoE packs 2.4T total parameters with 95B active, a 1M context window, and strong coding & agent capabilities. Start building:

Qwen3.8-Max is live on Fireworks, ready for agents, heavy coding, and long-context work. Fireworks is right there with us as a Day 0 launch partner. What a way to kick things off!It's Day 0, cue the F

arXiv:2608.12323v1 Announce Type: cross Abstract: Specifying a penalty can paradoxically convert a legal obligation into a cost-benefit calculation that favors violation. We demonstrate that this enfo

arXiv:2608.11588v1 Announce Type: new Abstract: Mobile GUI agents remain brittle when deployed to applications absent from source training. We study novel-app generalization under a limited target int

arXiv:2608.11252v1 Announce Type: new Abstract: Agentic AI systems routinely transport conclusions across biological, clinical and financial contexts, and the emerging safeguard is local verification:

arXiv:2608.11775v1 Announce Type: new Abstract: Gist-based context compression---summarising older conversation history into compact representations---is a common approach in long-horizon language mod

arXiv:2608.10627v1 Announce Type: new Abstract: Decompose-then-verify pipelines, including FActScore-style fact-checkers and long-form factuality evaluators, first split a passage into atomic claims b

arXiv:2608.10595v1 Announce Type: cross Abstract: Proteolysis-targeting chimeras (PROTACs) induce protein degradation by recruiting a target protein to an E3 ubiquitin ligase, making degradation a joi

arXiv:2608.09555v1 Announce Type: new Abstract: External natural-language skills provide large language model (LLM) agents with reusable and editable guidance for solving complex tasks. Yet their effe

arXiv:2608.09316v1 Announce Type: new Abstract: Offline context optimization improves an agent by revising its instructions and examples while keeping the model frozen. This approach learns from rollo

arXiv:2608.07631v1 Announce Type: cross Abstract: LLM-based full-duplex voice services allow users to speak while the assistant is responding. Because servers can generate output and advance dialogue

arXiv:2608.08630v1 Announce Type: new Abstract: Vision Language Models (VLMs) face significant challenges with ultra-long, interleaved image-text sequences due to the quadratic complexity of self-atte

I've been comparing Cline / Kilo / Qwen Code lately since they all handle long-task state differently. Cline: has Focus Chain, a markdown file kept outside the conversation that gets reinjected on a c

arXiv:2608.05759v1 Announce Type: new Abstract: Recognizing new and rare words - named entities, acronyms, domain specific special words, and other items scarce in training data - remains a key challe

arXiv:2503.15560v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly vulnerable to sophisticated multi-turn manipulation attacks, where adversaries strategically build conte

arXiv:2608.03031v1 Announce Type: new Abstract: Time series forecasting is fundamental to decision-making in complex systems, where future dynamics are influenced not only by historical observations b

Liquid AI released LFM2.5-2.6B today, and this might be more relevant to local AI than another massive model most people cannot run. The model is only 2.69B parameters, has 128K context, supports tool

arXiv:2606.15240v2 Announce Type: replace Abstract: Accurate vessel trajectory forecasting is essential for maritime situational awareness, navigation safety, traffic management, and autonomous naviga

Releasing Pokee-Isaac 28B — the world’s first real 10M-token context frontier-class agentic model, deployable on a single GPU (starting from RTX 4090 or equivalent). New proprietary non-decoder-only a

arXiv:2608.01314v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) increasingly rely on long chain-of-thought reasoning for complex tasks. However, as reasoning sequences lengthe

arXiv:2608.01400v1 Announce Type: new Abstract: Tabular foundation models, driven by in-context learning, have rapidly grown in quality and popularity. However, recent approaches with either cell-base

arXiv:2510.09935v2 Announce Type: replace Abstract: While memes are often humorous, they are frequently used to disseminate hate, causing serious harm to individuals and society. Current approaches to

Nate is right (full context can lead to a degradation of chats in several different ways) but you can't ask the AI about stuff like this as they have bad self-knowledge A good approach is to compact t

arXiv:2607.27959v1 Announce Type: new Abstract: Due to their strong generalizable multimodal processing and reasoning capabilities, Multimodal Large Language Models (MLLMs) have demonstrated significa

Cloud security startup Upwind Security Inc. today unveiled AI Agent Context Scanner, which inspects the instructions, tools and connections feeding artificial intelligence agents before those agents a

arXiv:2410.24035v2 Announce Type: replace-cross Abstract: Generating robust and reactive manipulation strategies that can adapt to changing context information is a challenging task in robotics. Over

arXiv:2607.26023v1 Announce Type: new Abstract: Graph foundation models (GFMs) have emerged as a promising paradigm for transferring knowledge across graph domains and tasks. Real-world graphs associa

arXiv:2607.25995v1 Announce Type: cross Abstract: Kubernetes is central to the cloud-native ecosystem, orchestrating containerised workloads. Recent work suggests that large language models (LLMs) can

arXiv:2607.25398v1 Announce Type: new Abstract: Language-model agents are increasingly deployed under standing instructions: a system prompt, a policy file, or a skills document is placed in context,

On benchmarking long-context agentic instruction following. Agent benchmarks mostly reward reaching the answer. This new benchmark measures whether the agent reached it the permitted way, which is the

arXiv:2607.23518v1 Announce Type: new Abstract: The rapid evolution of generative models has unlocked new potentials in protein binder design, a pivotal task in structural biology, by facilitating end

arXiv:2607.22711v1 Announce Type: cross Abstract: LLM coding agents operate by constructing trajectories that accumulate reasoning, tool calls, and results to enable multi-step decision-making. Howeve

LFM2.5-Encoder is a family of multilingual bidirectional encoders built on the LFM2 architecture, available in two sizes: LFM2.5-Encoder-230M — a lightweight encoder for tight latency and memory budge

Running local models means every token counts — an 8K or 16K window fills up fast when you're stuffing graph context into prompts for RAG. I benchmarked 10 graph serialization formats (JSON, GraphML,

“Generate a fake, but believable, witty Churchill insult at a party and explain the context. It should be very clever and original” This time, I think GPT 5.6 Sol Pro wins, but Fable is good too, and

Very cool idea to convert memory to skills. (bookmark it) Most agent memory systems retrieve past traces as passive context. MSCE turns them into executable skills instead. The training-free framework

arXiv:2511.23276v2 Announce Type: replace Abstract: Effective HFMD surveillance requires forecasts capturing both time-series patterns and contextual drivers such as school calendars, weather, and pol

arXiv:2607.13006v1 Announce Type: new Abstract: A growing family of indices scores how predictable a series is from its spectrum. Practitioners increasingly read these scores as answering a different

Context harnessing is super challenging to do right: what info needs to be collected, how to accumulate it into a knowledge graph, how to keep it up to date, etc... Super excited for @QodoAI, harnessi

arXiv:2604.05182v2 Announce Type: replace-cross Abstract: We introduce the Large Sparse Reconstruction Model to study how scaling transformer context windows affects feed-forward 3D reconstruction. Al

Elon Musk announced an upcoming comparison between Grok and Anthropic's Claude Opus with its 1M+ token context window. The post suggests xAI plans to demonstrate how Grok's capabilities compare to Cla

🤗 we just opensourced our tiny beast on @huggingface >0.9B ASR model >Apache license 2.0 >128k long-context transcription >Up to ~90-min audio input >Speaker labels + timestamps in one generation >Mul