Restez à la pointe de la tech

Intelligence Artificielle

IterCOMP: Reasoning-aware Adaptive Prompt Compression for Multi-hop Question Answering

arXiv:2608.13588v1 Announce Type: new Abstract: Multi-hop question answering requires complex reasoning across multiple evidence segments, which often overwhelms retrieval-augmented generation systems with lengthy and noisy contexts, thereby undermining both efficiency and accuracy. While existing prompt compression methods attempt to address this issue, they are typically…

Lire l'article

Intelligence Artificielle

Jais 2: A Family of Arabic-Centric Open Large Language Models

arXiv:2608.13580v1 Announce Type: new Abstract: Jais 2 is a family of Arabic-centric large language models developed jointly by MBZUAI, Cerebras, and Inception, designed to advance Arabic-centric language modeling, with strong performance across the Arabic and culturally grounded benchmarks evaluated in this report. The family includes, to our knowledge, the largest open…

Lire l'article

Intelligence Artificielle

BCMT: Blockwise Causal Memory Transformer

arXiv:2608.13578v1 Announce Type: new Abstract: Transformer architectures rely on dense self-attention to model long-range dependencies, but this mechanism exhibits quadratic complexity with respect to sequence length. We introduce BCMT (Blockwise Causal Memory Transformer), an architecture for long-context language modeling that decouples local token interactions from global…

Lire l'article

Intelligence Artificielle

Not All Tokens Are Equal: Inflation-Aware Routing for Agentic LLM Systems

arXiv:2608.13571v1 Announce Type: new Abstract: When a language model fails to answer a query on the first attempt, an agentic system retries, consuming additional tokens each time. This retry overhead creates a gap between what a model's per-token price implies and what a full workflow actually costs. We call this gap \emph{token inflation} and define it as the ratio of true…

Lire l'article

Intelligence Artificielle

Think in Latent, Explain in Language: Self-Explainable Latent Reasoning

arXiv:2608.13570v1 Announce Type: new Abstract: Latent reasoning has emerged as a powerful alternative to text-based Chain-of-Thought (CoT), offering significant gains in computational efficiency by compressing verbose reasoning into compact embeddings. However, compressing reasoning into the latent space renders the thinking opaque, hindering its interpretability. Current…

Lire l'article

Intelligence Artificielle

Does a Language Server Save Tokens for Coding Agents? A Measurement Methodology and Preliminary Study

arXiv:2608.13568v1 Announce Type: new Abstract: Coding agents spend most of their context budget on retrieval. Lexical retrieval (grep) is universal, instant, and zero-setup, but noisy: it cannot tell a definition from a call from a comment. Semantic retrieval via the Language Server Protocol (LSP) is precise and typed, but needs a running, indexed server and pays a…

Lire l'article