Search AI news

Introducing Claude Fable 5.2 and Claude Mythos 5.2

Our most capable models for daunting technical work, Claude Fable 5.2 and Claude Mythos 5.2 set a new bar in coding, finance, and the sciences.

ResServe: Accurate and Efficient FP4 LLM Inference with Residue Compensation

arXiv:2611.08713v1 Announce Type: new Abstract: Block-scaled 4-bit floating-point (FP4) quantization reduces large language model inference costs but can degrade task quality. Higher-precision computation can mitigate this loss at the expense of some of the efficiency gains from FP4 inference. Narrow matrix computations common in decoding often leave spare hardware capacity for low-cost precision recovery. ResServe combines an FP4 activation base with an FP4-quantized residue representing information lost during quantization. It uses this spare capacity to compute the residue's contribution and combines results on-chip, avoiding extra result transfers. We apply this principle to linear layers and decode attention, while selective compensation limits added work when processing input prompts. On NVIDIA B200, compensated linear kernels using the NVFP4 format improve numerical precision while retaining latency close to uncompensated execution for the evaluated operations with few rows. In the evaluated NVFP4 inference configurations, ResServe adds at most 3.4% request-latency overhead over W4A4 and reduces request latency by 22.4-53.3% relative to W4A8. Across five models, code-generation accuracy improves over same-format uncompensated inference, with mean relative gains of 15.04% for NVFP4 and 53.57% for MXFP4.

Selective, Risk-Controlled Emotion Forecasting in Conversation: From a Persistence Barrier to Departure Detection with Conformal Guarantees

arXiv:2611.05896v1 Announce Type: new Abstract: Forecasting emotion in conversation is increasingly framed as predicting the next emotional state's value. We show this targets a hard quantity in a state-observed testbed and propose a learnable, deployable reformulation instead. On valence-arousal-dominance trajectories from a dyadic corpus, repeating a speaker's own previous state sets a persistence baseline that no frozen-encoder correction meaningfully improves upon and a state-space filter exceeds; the floor requires the historical state to be observed, since an estimated anchor collapses persistence below a direct forecaster. What survives is the timing of a departure from persistence, learnable on three of four corpora and near chance on the highest-base-rate corpus, a negative result we report. We recast the task as selective departure forecasting: a lead-time-weighted metric with a leakage protocol, and commitment policies whose best choice switches with the departure rate. A dialogue-level conformal risk control bounds the expected loss of committed predictions, meeting the target in all twelve configurations tested, though the guarantee is bought through abstention, with coverage and alarm recall falling sharply on the hardest corpus. One tested language model's confidence fails as a ranking signal where another succeeds, a model-dependent failure not yet attributable to family versus scale. Code and result logs are available from the corresponding author upon request.

A thousand fewer paths to root

OpenAI built an autonomous pipeline that found, validated, and generated patches for 948 local privilege-escalation vulnerabilities in the Linux kernel.

Same Rule, Different Verdicts: Rubric Language and Clause Structure in LLM Judges for Korean Support Dialogues

arXiv:2611.04091v1 Announce Type: new Abstract: Services that operate in Korean often write their evaluation rubrics in Korean and hand them to an LLM judge. We test whether a judge's verdict depends on the language of the rubric and on how a rubric item is phrased. We write 12 criteria for support dialogues in four clause structures (affirmative, negated, conditional, exception) such that two pairs of structures have the same meaning, and we give each item in Korean and in English. Six low-cost models from three providers, plus one reference model, judge 60 translated ESConv dialogues and 144 constructed boundary cases under every combination (51,744 requests across the seven models). The analysis plan was fixed and committed before data collection. Cross-provider agreement is lower with Korean rubrics than with English rubrics (Cohen's kappa 0.687 vs. 0.745; difference -0.058, 95% CI [-0.072,-0.045]). Disagreement concentrates in negated, conditional, and exception items (odds ratio 5.6 relative to affirmative items). A single model changes its verdict between two items with the same meaning in 11-15% of cases. Two hypotheses are not supported: models from the same provider do not agree more than models from different providers, and adding paired examples does not reduce the language gap. We measure consistency only; no human labels are used, and all materials were drafted by an LLM.

Swapping the Judge Changes the Ranking: A Preregistered Study of Cross-Provider Replication in LLM-Judged System Comparisons

arXiv:2611.04090v1 Announce Type: new Abstract: Practitioners who compare systems with an LLM judge and have no human labels often check a conclusion by repeating it with a judge from another provider. We test how far that check can be trusted. In a preregistered study (with a disclosed post-registration reduction of the judge set), five judge models from three providers re-judged 4,000 Chatbot Arena battles (nine systems, 33 system pairs) that carry human votes, each in both response orders. Agreement with the human vote was low at the verdict level (median Cohen's kappa = 0.22), and system rankings did not survive a change of judge: Kendall's tau with the human ranking ranged from 0.17 to 0.89 (median 0.67), so the preregistered hypothesis that rankings remain stable was not supported. Conclusions replicated by two low-cost judges from different providers matched the human conclusion more often than single-judge conclusions (+0.10 precision), but the gain came from filtering out one poorly aligned judge, and replication involving that judge left a conclusion for only 35% of comparisons. Judges that agreed with humans reached a stable conclusion with no more verdicts than human votes required; the others failed to converge on 26-70% of system pairs at the sample sizes tested (up to 100 verdicts per pair). Disagreements with the human vote co-occurred across judges far more often than independence predicts, although a single human vote per battle cannot separate shared judge bias from voter noise.

FlatCake: A Flat KVCache Storage Architecture for LLM Serving

arXiv:2610.38355v1 Announce Type: new Abstract: KV cache reuse accelerates LLM serving, but existing systems manage host DRAM and NVMe SSD as a tiered hierarchy where DRAM acts as an intermediate cache. Production LLM workloads break both premises of this hierarchy. First, bimodal reuse defeats DRAM temporal filtering, since workloads are dominated either by one-shot blocks with long reuse distances or by multi-gigabyte agentic sessions that exceed DRAM capacity, putting SSD on the critical read path. Second, DRAM staging and eviction-ordered layout bottleneck SSD restoration. Holding host staging buffers for in-flight prefixes causes contention under load that aborts prefetches, while incremental eviction scatters a session's blocks across the SSD and prevents large sequential reads. We p

Polymathic AI and Princeton Researchers Release FlashMap, a Flow Map Drafter for 6.14x Faster LLM Decoding

FlashMap is a speculative decoding drafter from Polymathic AI, Princeton and USC ISI researchers. It drafts 16 tokens jointly in one pass and reaches up to 6.14x lossless speedup on Qwen3-8B. The post Polymathic AI and Princeton Researchers Release FlashMap, a Flow Map Drafter for 6.14x Faster LLM Decoding appeared first on MarkTechPost.

How Anthropic ships Claude with Claude: Separating the Brain from the Hands

Katelyn Lesse and Angela Jiang on Opus 5.5, the Claude Platform, and the engineering behind AI agents.

How Anthropic ships the #1 LLM in the World safely: Separating the Brain from the Hands

Katelyn Lesse and Angela Jiang join Latent Space to explain the engineering behind the Claude Platform: launching Opus 5.5, separating the model’s “brain” from the agent’s “hands,” scaling APIs, and building reliable managed agents. A new introduction ...

SLICE-Mem: Salience-Gated Lightweight Information Curation for Efficient LLM Agent Memory

arXiv:2610.33015v1 Announce Type: new Abstract: Long-term memory enables large language model (LLM) agents to maintain personalized and temporally coherent interactions, but repeated LLM inference for memory admission, extraction, and organization introduces substantial cost and latency. We present SLICE-Mem, a lightweight memory framework that combines salience-guided admission and predicate-centered information extraction. A compact classifier identifies user turns worth retaining, and a semantic-dependency-based extractor converts admitted turns into concise memory entries. This online pipeline requires no generative LLM calls, while cross-entry reconciliation is deferred to an offline consolidation stage. We evaluate SLICE-Mem on the weekly subset of Memora and LongMemEval-S using 8B a

Position, Role or Label? A Controlled Study of Instruction Conflicts in LLM Agents

arXiv:2610.33201v1 Announce Type: new Abstract: LLM agents take instructions from the operator, repository configuration, user, tool results and saved memory, which often conflict. Instruction-hierarchy benchmarks ask whether the higher-ranked source wins, but a source sets position, role and label at once. First, we build WhoWins, 1,080 code-scored scenarios in five task types, each with up to five mutually exclusive instructions, and seven controlled experiments that vary only how instructions are delivered. Second, we study 14 open-weight models (0.6B to 122B, thinking off and on) over 1,887,356 scored replies, checking main findings on held-out scenarios. Inside one message the first of two conflicting lines wins 72.42 to 94.66%, and across messages it keeps 22.95 to 62.65%. A policy s

Beyond On-Policy vs. Off-Policy: At What Level Should LLM Agent Distillation Follow the Student?

arXiv:2610.31918v1 Announce Type: new Abstract: Distilling interactive LLM agents requires choosing between teacher-generated demonstrations and student-generated experience, corresponding broadly to off-policy and on-policy distillation. While both have proven effective, we argue that this distinction is inherently hierarchical: the policy that induces an interaction history need not be the same as the policy that generates the token prefix of the current action. We introduce a hierarchical agent distillation framework that formalizes these two levels of on-policiness and enables explicit control over their pairing, mixture proportions, and training schedule. We study this problem through self-distillation, where a frozen teacher has access to task guidance unavailable to the student, and

Nanbeige Releases Nanbeige4.3-33B, a 33B Open Agentic Coding Model

Nanbeige LLM Lab released Nanbeige4.3-33B, a 33B dense Apache 2.0 model with 512K context. It reports 80.9 on Terminal-Bench 2.1 and will teach the upcoming Nanbeige4.3-3B. The post Nanbeige Releases Nanbeige4.3-33B, a 33B Open Agentic Coding Model appeared first on MarkTechPost.

Research on Modulating the Capability Distribution of Large Language Models via Singular Value Spectrum Intervention: Empirical Analysis of Llama and Qwen Models

An AI study published on October 24, 2026, on arXiv (ID 2610.30676v1) applied post-hoc singular-value spectrum smoothing and spike perturbations to five open-source Llama and Qwen instruction-tuned models, finding that this lightweight intervention can systematically reshape the trade-offs in model performance across three capability domains: factual knowledge, language understanding, and deductive reasoning.

Why it matters：This paper is the first to empirically demonstrate, within a multi‑model, multi‑task framework, the causal impact of the singular value spectrum of transformer feedforward layers on downstream capabilities, revealing structurally sensitive patterns in capability allocation and offering a new pathway for decoupling model capabilities and enabling controllable editing. All conclusions are based on publicly available models and standard benchmarks, with transparent methods and comprehensive evaluation dimensions.

Qwen2.5-1M: Deploy Your Own Qwen with Context Length up to 1M Tokens

Tech Report HuggingFace ModelScope Qwen Chat HuggingFace Demo ModelScope Demo DISCORD Introduction Two months after upgrading Qwen2.5-Turbo to support context length up to one million tokens, we are back with the open-source Qwen2.5-1M models and the corresponding inference framework support. Here’s what you can expect from this release: Opensource Models: We’re releasing two new checkpoints, Qwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1M, marking the first time we’ve upgraded our opensource Qwen models to handle 1M-token contexts.

Qwen2.5: A Party of Foundation Models!

GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD Introduction In the past three months since Qwen2’s release, numerous developers have built new models on the Qwen2 language models, providing us with valuable feedback. During this period, we have focused on creating smarter and more knowledgeable language models. Today, we are excited to introduce the latest addition to the Qwen family: Qwen2.5. We are announcing what might be the largest opensource release in history!

Qwen2.5-Math: The world's leading open-sourced mathematical LLMs

GITHUB HUGGING FACE MODELSCOPE DISCORD 🚨 Qwen2.5-Math mainly supports solving English and Chinese math problems through CoT and TIR. We do not recommend using this series of models for other tasks. Introduction A month ago, we released the first series of mathematical LLMs - Qwen2-Math - of our Qwen family. Today, we have upgraded it and open-sourced Qwen2.5-Math series, including base models Qwen2.5-Math-1.5B/7B/72B, instruction-tuned models Qwen2.5-Math-1.5B/7B/72B-Instruct, and mathematical reward model Qwen2.

Qwen2-Audio: Chat with Your Voice!

DEMO PAPER GITHUB HUGGING FACE MODELSCOPE DISCORD To achieve the objective of building an AGI system, the model should be capable of understanding information from different modalities. Thanks to the rapid development of large language models, LLMs are now capable of understanding language and reasoning. Previously we have taken a step forward to extend our LLM, i.e., Qwen, to more modalities, including vision and audio, and built Qwen-VL and Qwen-Audio. Today, we release Qwen2-Audio, the next version of Qwen-Audio, which is capable of accepting audio and text inputs and generating text outputs.

Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters

GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD Introduction Since the surge in interest sparked by Mixtral, research on mixture-of-expert (MoE) models has gained significant momentum. Both researchers and practitioners are keenly interested in understanding how to effectively train such models and assessing their efficiency and effectiveness. Today, we introduce Qwen1.5-MoE-A2.7B, a small MoE model with only 2.7 billion activated parameters yet matching the performance of state-of-the-art 7B models like Mistral 7B and Qwen1.