Sampling multiple solutions and returning the majority answer is among the most reliable ways to improve the reasoning accuracy of large language models without labels, and a growing family of methods converts this consensus signal into training supervision. However, existing approaches use consensus only in restricted forms: as a filter that selects solutions for fine-tuning, as a preference between answers, or as a scalar reward for reinforcement learning, discarding most of the information that the agreeing solutions contain.
LLM agents are increasingly evaluated on multi-week decision tasks in which the state that drives cost is never directly observed. On such tasks the final cost cannot say why an agent failed: it may have misread the world, or read it correctly and still failed to act (the knowing-doing gap).
Automatic scientific discovery has long been a goal of computational scholars - a machine that can discover nature's secrets on its own, moving computational systems beyond data-fitting tools toward the generation and refinement of mechanistic models of the universe. Recent advances in symbolic regression (SR) and large-language-model (LLM)-based agents suggest that such systems can recover equations from data, incorporate domain priors, and automate parts of the research workflow.
Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks. Yet nearly all existing approaches, from graph-structured memories to reflective insight stores, access memory through fixed, hand-designed heuristics.
Identifying root causes in production microservice failures requires reasoning over large-scale, multimodal telemetry spanning metrics, logs, and traces, a problem that has proved resistant to both classical and LLM-based approaches. The OpenRCA dataset exemplifies these challenges: it is large-scale, multimodal, and lacks detailed domain knowledge, and yields consistently low accuracy across all existing methods.
While traditional graphics methods often synthesize 3D indoor scenes autoregressively or hierarchically, recent vision-language model (VLM)-based generators predominantly adopt a one-shot paradigm where the full layout is planned at once. This one-shot approach often requires global re-optimization or complete reconstruction during interactive editing (e.
We introduce ExTernD (Expanded-rank Ternary Decomposition), a post-training factorization of each LLM weight matrix $A \in \mathbb{R}^{m \times n}$ into $A \approx B \mathrm{diag}(D) C$ with ternary factors $B \in \{-1,0,+1\}^{m \times k}$, $C \in \{-1,0,+1\}^{k \times n}$ and a real scale vector $D \in \mathbb{R}^k$. The inner rank $k = μ\min(m,n)$ is deliberately expanded beyond full rank ($μ> 1$), so that components past full rank correct the quantization error of earlier ones.
Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and harmful intermediate interactions. We propose LOTAPO , a self-generated process-supervision method based on backward leave-one-turn attribution.
Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and harmful intermediate interactions. We propose LAPO, a self-generated process-supervision method based on backward leave-one-turn attribution.
Although multimodal large language models (MLLMs) have achieved remarkable progress, understanding 3D spatial relationships from 2D images remains a critical challenge. Existing methods primarily rely on symbolic text tokens, which inherently lack the fidelity to represent continuous geometric information.
arXiv:2607. 12986v1 Announce Type: new Abstract: Plan evaluators can reward a strategic plan for becoming less explicit.
By Aleh Manchuliantsau
arXiv:2607. 12295v1 Announce Type: cross Abstract: The rapid integration of artificial intelligence (AI) and generative AI (GenAI) into education presents significant opportunities to enhance teaching and learning, while raising ethical concerns about the responsible use of these technologies in educational settings.
By Akriti Bagale, Nafisa Mehjabin, Ali \"Unl\"u, Aditya Johri
arXiv:2605. 05686v3 Announce Type: replace Abstract: Language models draw on two knowledge sources: facts baked into weights (parametric memory, PM) and information in context (working memory, WM).
By Qiyao Liang, Risto Miikkulainen, Ila Fiete
arXiv:2607. 12085v1 Announce Type: new Abstract: Evaluating retail conversational agents requires methods beyond lexical-overlap metrics to assess intent alignment, factuality, helpfulness, clarity, tone, and overall response quality.
By Niranjan Kumar M, Balaji Nagarajan, Karthik Nair, Faysal Satter, Nithin Surendran
arXiv:2607. 12787v1 Announce Type: new Abstract: Recent advances in multimodal large language models (MLLMs) have significantly improved the performance of multimodal emotion recognition (MER) and enabled interpretable description generation by jointly modeling video, audio, and language, etc.
By Kaiwen Zheng, Junchen Fu, Wenhao Deng, Hu Han, Joemon M. Jose, Xuri Ge
arXiv:2607. 12480v1 Announce Type: new Abstract: This paper defines TRACE (Typed Reasoning And Commitment Evidence): a typed, versioned schema for recording reasoning traces, a reference procedure for writing records against it, and one operating discipline, no durable state change without a record.
By Edward Y. Chang, Emily J. Chang
arXiv:2607. 12550v1 Announce Type: new Abstract: The key-value (KV) cache has become the dominant memory cost of transformer inference.
By Rahul Krishnan, Volker Schulz
arXiv:2607. 12175v1 Announce Type: cross Abstract: X-ray tomography enables nondestructive characterization of material microstructures, while advances in micro-CT imaging have accelerated volumetric data acquisition and reconstruction.
By Pradyumna Elavarthi, Arun J. Bhattacharjee, Harrison Lisabeth, Anca Ralescu, Petrus H. Zwart, Dilworth Parkinson, Elizabeth G. Clark
arXiv:2507. 15833v3 Announce Type: replace-cross Abstract: Human vision is a highly active process driven by gaze, which directs attention to task-relevant regions through foveation, dramatically reducing visual processing.
By Ian Chuang, Jinyu Zou, Andrew Lee, Dechen Gao, Iman Soltani
arXiv:2607. 12520v1 Announce Type: new Abstract: What a frontier model recalls about a person or tool from its own weights -- before any retrieval step -- often shapes the first description a human sees, making that parametric corpus presence a measurement problem.
By Bojie Li, Noah Shi