2026年9月21日 技术热点总结

项目简介：Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.

技术栈：Python、apple-silicon、decision-model、inference、laya、local-ai、machine-learning、mlx、modernbert

核心介绍：中文 · Benchmarks · Snake demo · Hugging Face weights The GIF is an original-speed render of a real local Snake run. Every move calls Laya; the visible cycle safety layer can correct unsafe proposals. The latency figures above are the separate one-question API benchmark, not the frame time of the three-question Snake loop. Watch the 30-second …

项目简介：Local typed decisions, contrastive data curation, and model evaluation.

技术栈：Python

核心介绍：Model · Capabilities · Quickstart · Methodology · Documentation and development · Citation Nimble takes some text and a schema, and makes typed decisions about the text. The schema is the list of questions to answer. Each question is either a choice from a list that you give or a true or false question. For each question, Nimble returns the answer it picked and the probability of each allowed answer. Nimble makes each decision in one step and does not write out any reasoning

项目数据：…

项目简介：tiny Jev-like family of decision models built on top of Qwen3.5 you can train and run on your own

技术栈：Python、decision-model、jev、qwen3

核心介绍：Small Jev-like decision models you can train and run yourself. Kev is a family of small decision models built on Qwen3.5 and based on the architecture described in Jev’s Architecture Unmasked. You can use the pretrained weights or train your own. The API matches TypeSafe’s System One, so you can point their Python SDK at your local server.

关键特性：0.8B, 4B, and 9B models, with training code and evaluation data.；Yes/no (noul), mu…

LLM assistants are widely used for daily social advice, yet evaluating their social reasoning in such consultation settings remains challenging since (i) it requires setups where the assistant learns about social situations from subjective user narratives, and (ii) social properties, such as others' intentions, typically lack verifiable ground truth. To address these challenges, we introduce Fuse, a multi-agent simulation framework for studying user-mediated social reasoning. In Fuse, a target agent with a hidden motive interacts with other agents including one representing the user, who th…

Information retrieval is increasingly important as LLM agents tackle complex tasks involving diverse information needs. Because retrieval relies on an index that represents each document through index keys, retrieval quality depends heavily on how effectively these keys expose the knowledge contained in each document. However, effective index representations vary across retrieval environments, making it difficult for any fixed optimization strategy to perform consistently. Yet evolving an index to its retrieval environment remains largely human-driven, requiring humans to diagnose retrieval…

Test-time scaling can improve large language model reasoning by generating and combining multiple candidate responses. In sampling-based methods, the inference budget is often described by the number of generated candidates, N. However, N tells us how many candidates are generated, not how they are executed. The same candidate budget can be produced in one batched generation call or split across several sequential calls with smaller batch sizes. We first study the effect of increasing N on reasoning accuracy using Phi-3-mini and Qwen2.5-1.5B on 500 GSM8K prompts. As expected, increasing N f…

Question answering has advanced rapidly with large language models, but predominantly for high-resource languages, in both text and spoken settings. Spoken question answering (SQA) benchmark for Telugu remains unexplored, and the reliability of automatic evaluation in this setting remains unquantified. We introduce VākQA, a Telugu SQA benchmark of 2,001 factoid question-answer pairs across six domains, with 2.53 hours of speech audio, bilingual transcriptions, and human-verified reference answers. We first validate evaluation methods against human judgements: Gemini-as-a-judge best approxim…

Agent trajectories record what an agent does and what happens next. Yet standard supervised fine-tuning (SFT) applies loss only to agent-authored action tokens, using environment observations as context but not as prediction targets. We ask whether this convention provides the best initialization for subsequent reinforcement learning. We introduce ActObs, which also supervises the observation tokens already present in each trajectory. Although deployed agents never generate observations, learning to predict them encourages the policy to model action consequences without adding data, paramet…

We present Srijika, a system for producing installable OpenType fonts for nine Brahmic scripts: Devanagari, Tamil, Bengali, Telugu, Kannada, Malayalam, Gujarati, Gurmukhi, and Odia. Rather than generating fonts from scratch, Srijika restyles glyph outlines from shaping-complete template fonts. It preserves the template's cmap and GSUB closure and its GPOS data under a documented metric policy, making every output a complete font by construction. This addresses a central challenge of Indic font generation: hundreds to thousands of conjuncts, half forms, and matra variants must remain mutuall…