Showing 111 dispatches curated by Neural Pulse AI
Tool-using agents repeatedly carry observations whose useful content can be much smaller than their original payload.
Knowledge Graph (KG) quality depends not only on downstream graph validation, but also on the quality of tabular metadata used before integration.
Aerial vision-and-language navigation (VLN) agents are typically trained on detail-rich, trajectory-aligned commands, whereas users issue short, intent-driven instructions; on a frozen OpenFly navigator, this \emph{instruction gap} drops success rate (SR) from $31.03\%$ to $11.33\%$.
Tool-calling agents have become central to enterprise AI, yet training and evaluating them at scale remains severely constrained due to business and legal restrictions on enterprise systems, data, and database schemas.
Self-improving LLM agents can adapt a credit pipeline to a changed rule, but an agent that rewrites itself destroys the artefact a supervisor reviews: a named change, a recorded test, an approval.
Agentic
Plan-and-
As AI systems increasingly interact with people and make decisions about them, understanding human interpretations becomes an important part of developing human-centered AI.
Large Language Models (LLMs) have achieved remarkable capabilities but remain vulnerable to jailbreak attacks that elicit harmful or unsafe outputs.
AI research agents are increasingly used to search over programs, mathematical constructions, and proofs.
The Offline AI Modules workstream enables practical, low-power, and community-accessible deployment of voice-first AI systems that operate fully offline.
Task planning for LLM agents requires workflows that satisfy both user intent and complex sub-task dependencies.
Vision-language models (
CuratorMAS
The evolution of machine learning has progressively changed where intelligence resides in an AI system.
Prefill-decode disaggregation is becoming a common architecture for LLM serving because it separates two phases with distinct execution patterns and SLO objectives.
Recent advances in Large Language Models (LLMs) have demonstrated remarkable capabilities in web front-end execution, with browser-based game generation emerging as a particularly prominent frontier.
We study how Vision Transformers ground abstract concepts (e.g., angry) when training data provide limited direct referential evidence.
Artificial intelligence has advanced individual radiotherapy tasks, yet these capabilities remain separated across clinical stages, software environments and data modalities.
Traditional data pipelines are notoriously brittle, often failing due to upstream schema drift, API contract changes, or website DOM modifications.
Large language model
Large language models (
Agent harnesses make many small, typed decisions per task: which model to call, which tool to use, whether retrieved text is relevant, whether an input carries an injection.
Societal resilience research relies on access to useful and actionable data, which motivates our main research question: Can annual reports, processed at scale with LLMs, provide a useful signal about how companies disclose their response to AI?
DeRe
Interactive world models are increasingly capable of generating environments and acting within them, yet deliberately editing an existing executable world remains underexplored.
Diffusion models trained with
Graphics processing unit (GPU) generations scale matrix, special-function, and memory pipelines at different rates, so kernel bottlenecks move as hardware evolves.
Four-bit floating-point (FP4) Tensor Cores accelerate matrix multiplication, but scale computation, operand packing, layout construction, and saved backward state can erase the gain.
Adam's geometric
Kolmogorov-Arnold Networks
Customer churn prediction on the IBM Telco Customer Churn benchmark (n = 7,043) routinely reports test accuracies above 95%, with the most cited published study reporting 99.01%.
Many machine learning (ML) applications rely on expert labels, and qualified experts may provide different but plausible interpretations of the same observation.
Humans express uncertainty verbally via markers (e.g., "possible," "likely"), yet most LLM uncertainty quantification (UQ) relies on costing likelihood- or consistency-based signals.
Fixed-size recurrent memory limits storage growth during inference, but successful recall depends on the task and training.
Memorization
PRM-
Long-horizon language agents increasingly rely on external memory as a frozen world model, yet current memory systems are usually judged only by task success or token cost.
K-Dense BYOK
Agent harnesses increasingly want to run small language models (SLMs) on the microtasks around a frontier large language model (LLM) planner: auto-approving shell commands, writing memory, selecting tools, ranking past turns.
Detailed profession-
On 40
LLM agents
Build2SPARQL
Public-service recommendations require evidence that matches the requested service, scope, and date.
Large language models (LLMs) can influence people's beliefs, yet little is known about whether and how they can manipulate each other.
We present AREX-2, an effort to advance the self-improving capability of LLM agents, which we define as the ability to iteratively refine a solution at test time.
When a materials LLM answers a question about crystal structure, does it reason from the structure or copy an answer already printed in its input?
Vision-language models may rewrite anomalous text in images into linguistically plausible expressions, compromising OCR transcription faithfulness.
When a student is stuck, a tutor faces the assistance dilemma: help given too early can hinder productive struggle, while help withheld too long leaves the student in a frustrating, persistent impasse (i.e., wheel spinning).
Is human readability necessary for effective fine-tuning of large language models?
Automated generation of LLM harnesses promises to improve inference through task specialization.
In July
Sparse-autoencoder decomposability and concentrated feature attribution are increasingly treated as evidence that a model's computation is easier to reverse-engineer.
Young people increasingly turn to General-Purpose Conversational Agents (GPCAs), such as ChatGPT, in moments of distress.
Large Language Model (LLM)-based agents increasingly self-evolve by editing a persistent skill document that encodes their workflow, tool-use rules, and decision logic.
The pursuit of recursive self
D-peptides combine protease resistance with high target specificity, but computational design of D-peptide binders remains immature.
Power system operation is a safety-critical sequential decision-making problem, making it a natural testbed for reinforcement learning (RL).
CryoEM map interpretation requires features that are spatially localized, consistent across samples, and informative across spatial scales.
Audio large language models
Benchy is a semantic language and execution engine for benchmarking AI programs.
Large Language Models (LLMs) have demonstrated historic breakthroughs in general reasoning with early successes in biomedical science.
While large language models (LLMs) have achieved remarkable linguistic capabilities, a profound question lingers at their core: do these models truly comprehend context or simply excel at pattern matching on an unprecedented scale?
Large language models (LL
Large-scale recommenders increasingly adopt the sequential generative recipe behind large language models, bringing the Transformer into recommendation along with design choices made for text, including Rotary Position Embedding (RoPE).
Platform policies are increasingly tested on artificial users, making agent fidelity important.
Agentic AI systems are increasingly being explored in medical imaging to improve throughput and reduce clinician workload; however, safe deployment remains challenging because autonomous errors may propagate into downstream clinical decisions.
While inference-time reasoning in large language models (LLMs) promises better decision making, its higher computational cost may not yield better economic outcomes.
Evaluating explainable Artificial
Data Spaces enable sovereign and governed data sharing across organizational boundaries, but their integration with AI agents remains challenging due to mismatches between probabilistic language model interactions and policy-driven data infrastructures.
The purpose of this article is to highlight the central role of autonomous systems as the ultimate stage in the development of AI, to explain the underlying technical challenges that require a combination of connectionist AI and symbolic AI, and to integrate AI and systems engineering.
This paper
Pretrained ASR systems perform poorly on noisy Broadcast Police Communication (BPC), hindering efforts to understand police decision-making.
Agents are increasingly deployed with real autonomy in web application and network penetration testing, where a single out-of-scope action can breach a client's engagement boundary.
When one language model judges whether another's code is correct, it does not report the absence of evidence.
Role-playing agents based on large language models have been widely applied in areas such as personalized assistance and social simulation.
DNA sequencing
Policy interventions propagate through public communication, institutional decisions, and stakeholder responses, yet datasets for financial multi-agent simulation rarely connect these processes to temporally aligned historical evidence.
We introduce the Pistis model family, comprising 27B- and 9B-parameter multimodal large language models built on Qwen3.6 and Qwen3.5, respectively, and developed through a general and scalable post-training framework.
Object permanence and solidity are hallmarks of human cognitive priors.
TW3Cast is a
TWIST is
Forecasting agents increasingly combine language-model reasoning, retrieval, ensembling, and calibration, but it remains unclear when each behavior should be trusted.
Faithful user simulation is fundamental to building, evaluating, and improving interactive AI at scale.
Artificial Intelligence agents based on large language models provide convenient natural language interfaces to scientific software, but reliability is not automatic.
Chain-of-thought (CoT) monitoring assumes that the reasoning a model writes reflects the computation that directly produces its answer.
The objective of this article is to provide design principles and a software architecture for enabling interaction between humans and multiple agents in simulated dynamic worlds.
Dependency conflicts in Python ecosystems arise from incompatible version constraints, missing packages, and undocumented compatibility relationships, causing many real-world code snippets to fail at execution.
JAZ
Mathematical reasoning benchmarks are typically organized by topic, but language models may organize their internal computation by reusable reasoning approach instead.
Reinforcement
Agentic AI systems are increasingly adopting automated pipelines that integrate multiple tools.
This paper introduces a novel
TwinCheck
Multi-Objective Direct Preference
Policy-
Language-model
Researchers report correlated errors among LLM judges, so agreement between judges may overstate the evidence.
Visual impairment affects over 2.2 billion people worldwide, yet conventional white canes cannot detect elevated hazards or provide semantic environmental context.
Researchers introduce AutoGym, a framework for generating agent-training tasks with executable environments and verifiers.
Medical large language models are commonly trained on mixtures of didactic data (e.g., textbooks) and clinical data (e.g., patient records), yet how these data types differentially shape model capabilities remains unclear.
Process discovery rarely yields a single coherent process structure.
International law provides the normative framework through which states coordinate action, regulate armed conflict, and protect human rights, yet its texts remain without token-level named entity recognition (NER) resources.
Mobile river monitoring robots must interpret obstacles and water boundaries that geographic waypoints alone cannot describe.
Behavioural evaluations of hosted language models can vary because the evaluated service, the measurement instrument, or both differ across runs.
AI systems are becoming participants in the evaluation and use of scientific research.
The aggregation of many lay estimates often outperforms individual expert judgment, a phenomenon known as the wisdom of crowds.
Enterprise AI assistants must produce responses that are verifiable and traceable to source evidence.
Large language model (LLM) judges provide a flexible and scalable method for evaluating model and agent outputs, but their verdicts can be sensitive to incidental changes in the evaluated response, judge instructions, and scoring rubric.