Weekly Digest•Original source: Neural Pulse
AI news this week: 31 source-linked stories
A dated list of 31 AI stories with links to their original sources.
News desk:Scheduled updates; publication dates vary.
|
Providers Monitored:Anthropic, OpenAI, arXiv, Hugging Face, NVIDIA
Latest indexed date: 2026-10-11Dated source-linked stories; claims are not independently verified.Browse all 135 news stories ↓
Featured storyAI Research•Friday, October 9, 2026
Agent-Controlled Forgetting for Tool-Using Agents: Reversible Context Curation in Practice
Tool-using agents repeatedly carry observations whose useful content can be much smaller than their original payload.
Read storySource attribution: arXiv (cs.AI); not independently verified.
⚡ Open-Source Radar
Trending & Novel AI Repositories
Curated directly from GitHub telemetry • Updated hourly
Autonomous Agents★ 277.2k
affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Code...
JavaScriptGitHub ↗
Autonomous Agents★ 252.8k
NousResearch/hermes-agent
The agent that grows with you
PythonGitHub ↗
Autonomous Agents★ 247.5k
deepseek-ai/deepseek-harness
DeepSeek Harness: Everything is a Plugin.
TypeScriptGitHub ↗
Developer Tools★ 212.7k
anomalyco/opencode
The open source coding agent.
TypeScriptGitHub ↗
Developer Tools★ 195.0k
ultraworkers/claw-code
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
RustGitHub ↗
Autonomous Agents★ 190.5k
firecrawl/firecrawl
Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥
TypeScriptGitHub ↗
Foundation Models★ 187.5k
Significant-Gravitas/AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on w...
PythonGitHub ↗
DeepSeek Ecosystem★ 182.8k
ollama/ollama
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
GoGitHub ↗
🚀 Indie AI Launchpad & Hidden Gems
Emerging & Actively Maintained Repositories
Curated independent AI tools and experimental research under 500 stars with active commits.
Embodied AI★ 293
Hebbian-Robotics/hflow
SDK for robotics teams to verify the quality of their data used for AI model training.
PythonUpdated 2026-10-11
Indie Tool★ 272
squirrelscan/squirrelscan
The website QA tool for your coding agent. 300+ audit rules across SEO, performance, security, accessibility and agent experience.
TypeScriptUpdated 2026-10-11
Indie Tool★ 232
jasoncheng7115/jt-doc-tools
An all-in-one PDF and Office document platform: self-hosted, open source, under your control. 整合式 PDF / Office 文件處理平台，自架、開源、可控。
PythonUpdated 2026-10-11
Local AI★ 201
KyaniteLabs/kinocut
Guardrailed video editing MCP server for AI agents. FFmpeg, Hyperframes, repurposing tools, Python client, and CLI. Local, fast, free.
PythonUpdated 2026-10-11
Indie Tool★ 97
ypollak2/llm-router
Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cut...
PythonUpdated 2026-10-11
Experimental Agent★ 91
sleep2agi/agent-network
助力搭建你的数字 AI 员工军团 — 多 Agent 一行命令组网协作。Claude Code / Claude Agent SDK / Codex / Grok Build 4 runtime + 8+ 家 LLM（Anthropic / OpenAI / xAI / Mini...
TypeScriptUpdated 2026-10-11
Embodied AI★ 77
Frank-ZY-Dou/awesome-ai-3d-modeling-robotics
Source-linked examples of AI models used for 3D modeling, industrial design and CAD, and robot control, with archived media and the model na...
PythonUpdated 2026-10-11
Experimental Agent★ 71
objectstack-ai/objectstack
The ontology is the software. One executable business ontology: AI writes it, the runtime runs it, agents operate it, you own it. Open proto...
TypeScriptUpdated 2026-10-11
📋Latest Executive Briefing
View All Weekly Briefings →⚡ Continuous Wire Stream
135 Stories IndexedAI Research•Original source: arXiv (cs.AI)
Agent-Controlled Forgetting for Tool-Using Agents: Reversible Context Curation in Practice
Tool-using agents repeatedly carry observations whose useful content can be much smaller than their original payload.
AI Research•Original source: arXiv (cs.AI)
An Explainable Header-Centric Framework for Large-Scale Semantic Table Interpretation and Data Quality Assessment
Knowledge Graph (KG) quality depends not only on downstream graph validation, but also on the quality of tabular metadata used before integration.
AI Research•Original source: arXiv (cs.AI)
Speaking the Navigator's Language: Trajectory-Grounded Instruction Translation for Frozen Aerial VLN Agents
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 $11.33\%$.
AI Research•Original source: arXiv (cs.AI)
Synthesis Through Simulation: Generating Coherent Enterprise Data via Scalable Agent-System Interaction
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.
AI Research•Original source: arXiv (cs.AI)
The Harness as the Only Mutable Surface: Compliance-Bounded Self-Evolution of LLM Agents in Credit Pipelines, with a Measured Admission Gate
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.
AI Research•Original source: arXiv (cs.AI)
Verification and Self-Improvement in Agentic AI: Foundations and Limits
Agentic
AI Research•Original source: arXiv (cs.AI)
Plan-and-Patch: Diffusion Language Models for Agentic Planning
Plan-and-
AI Research•Original source: arXiv (cs.AI)
Whose Ground Truth? Embracing Ambiguity in Human-Centered AI
As AI systems increasingly interact with people and make decisions about them, understanding human interpretations becomes an important part of developing human-centered AI.
AI Research•Original source: arXiv (cs.AI)
Beyond Refusal Patterns: Safe-Role Internalization for Robust and Generalizable LLM Safety Alignment
Large Language Models (LLMs) have achieved remarkable capabilities but remain vulnerable to jailbreak attacks that elicit harmful or unsafe outputs.
AI Research•Original source: arXiv (cs.AI)
EPOCH: Reliable Discovery through Evidence-Governed Search
AI research agents are increasingly used to search over programs, mathematical constructions, and proofs.
Robotics & Hardware•Original source: NVIDIA AI Blog
Into the Omniverse: How Developers Turn Ideas Into Simulations With Frontier AI Agents
Turning a simulation idea into a working application means assembling assets, connecting physics and rendering, and checking that the scene behaves as intended.
AI Research•Original source: arXiv (cs.AI)
Offline AI Modules: Voice-First Offline Architecture, Hardware Reference Stack, Quantization and Benchmarking
The Offline AI Modules workstream enables practical, low-power, and community-accessible deployment of voice-first AI systems that operate fully offline.
AI Research•Original source: arXiv (cs.AI)
Topology-Consistent Task Planning over Cellular Workflow Complexes for LLM-based Agents
Task planning for LLM agents requires workflows that satisfy both user intent and complex sub-task dependencies.
AI Research•Original source: arXiv (cs.AI)
When to Rethink: Learning Multi-Perspective Self-Verification for Vision-Language Models
Vision-language models (
AI Research•Original source: arXiv (cs.AI)
CuratorMAS: Automating Dataset Curation via Multi-Agent Orchestration
CuratorMAS
AI Research•Original source: arXiv (cs.AI)
Smart Content Ingestion for Generative AI Workloads
The evolution of machine learning has progressively changed where intelligence resides in an AI system.
AI Research•Original source: arXiv (cs.AI)
FluidPD: In-Place Elasticity for SLO-Aware Prefill-Decode Disaggregated LLM Serving
Prefill-decode disaggregation is becoming a common architecture for LLM serving because it separates two phases with distinct execution patterns and SLO objectives.
AI Research•Original source: arXiv (cs.AI)
GAMEGO: Training Game-Dev Agents with Synthetic Trajectories Anchored in Real-World Assets
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.
LLMs & Foundation Models•Original source: Anthropic Newsroom
Introducing Claude Haiku 5.5
Our fastest, cheapest, and most capable small model yet.
AI Research•Original source: arXiv (cs.AI)
Metonymic Circuits for Abstract Concept Grounding in Vision Transformers
We study how Vision Transformers ground abstract concepts (e.g., angry) when training data provide limited direct referential evidence.
Robotics & Hardware•Original source: NVIDIA AI Blog
NVIDIA, Microsoft Kick Off a New Beginning for Windows PCs With RTX Spark and AI Agents
At a
AI Research•Original source: arXiv (cs.AI)
RadOnc-Agent: An LLM-Orchestrated Framework for AI Workflows Across the Radiotherapy Care Pathway
Artificial intelligence has advanced individual radiotherapy tasks, yet these capabilities remain separated across clinical stages, software environments and data modalities.
AI Research•Original source: arXiv (cs.AI)
AegisFlow: A Multi-Agent Agentic AI Framework for Autonomous Remediation and Self-Healing in Fragile Data Ecosystems
Traditional data pipelines are notoriously brittle, often failing due to upstream schema drift, API contract changes, or website DOM modifications.
AI Research•Original source: arXiv (cs.AI)
Principles that Guide, Actions that Inform: Agent Evolution via Knowledge Abstraction
Large language model
Robotics & Hardware•Original source: NVIDIA AI Blog
Why Telecom Operators Are Building Their AI Strategy on Open Models
Telecom operators are
AI Research•Original source: arXiv (cs.AI)
Choosing Before Acting: Comparative Value Estimation for Long-Horizon Tool-Use Agents
Large language models (
AI Research•Original source: arXiv (cs.AI)
Fast Models, Slow Evidence: A Paired and Self-Audited Evaluation of System-1 Decision Models for LLM Agent Harnesses
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.
Robotics & Hardware•Original source: NVIDIA AI Blog
From Scan to Treatment Plan, AI Helps Close Breast Cancer’s Deadliest Gaps
Breast cancer is the most
AI Research•Original source: arXiv (cs.AI)
The AI Risk Observatory: What Can We Learn from AI Disclosures in Annual Reports About Societal Resilience?
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?
AI Research•Original source: arXiv (cs.AI)
DeReAct: Decomposed Reasoning and Acting for Reliable AI Agents
DeRe
AI Research•Original source: arXiv (cs.AI)
World Editing: Intervening on Executable Worlds at Increasing Depth
Interactive world models are increasingly capable of generating environments and acting within them, yet deliberately editing an existing executable world remains underexplored.
Weekly Digest•Original source: Neural Pulse
AI news this week: 56 source-linked stories
A dated list of 56 AI stories with links to their original sources.
AI Research•Original source: arXiv (cs.LG)
Energy Time-Series Imputation with Differentially Private Diffusion Models via Clipping-Aware Objective Conditioning
Diffusion models trained with
AI Research•Original source: arXiv (cs.LG)
Fast Polynomial Transcendentals for LLMs
Graphics processing unit (GPU) generations scale matrix, special-function, and memory pipelines at different rates, so kernel bottlenecks move as hardware evolves.
AI Research•Original source: arXiv (cs.LG)
Format-Aware Fusion for Fast FP4 Pretraining
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.
AI Research•Original source: arXiv (cs.LG)
How Far is Adam from Natural Gradient Descent?
Adam's geometric
AI Research•Original source: arXiv (cs.LG)
SW-KAN: Kolmogorov-Arnold Networks with Stieltjes-Wigert q-Orthogonal Polynomials
Kolmogorov-Arnold Networks
AI Research•Original source: arXiv (cs.LG)
The Hidden Costs of 99% Accuracy: A Trustworthiness Audit of the Telco Customer Churn Benchmark
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%.
AI Research•Original source: arXiv (cs.LG)
Uncertainty-Aware Learning from Multi-Expert Interval Targets
Many machine learning (ML) applications rely on expert labels, and qualified experts may provide different but plausible interpretations of the same observation.
AI Research•Original source: arXiv (cs.LG)
"very likely" Means "uncertain"? How LLMs Diverge from Humans in Linguistic Uncertainty Quantification
Humans express uncertainty verbally via markers (e.g., "possible," "likely"), yet most LLM uncertainty quantification (UQ) relies on costing likelihood- or consistency-based signals.
AI Research•Original source: arXiv (cs.LG)
Constant-Memory Recall: Learned Associations in a Fixed Matrix State
Fixed-size recurrent memory limits storage growth during inference, but successful recall depends on the task and training.
AI Research•Original source: arXiv (cs.LG)
The Null Is the Hard Part: Exact Tests for Memorization in Generative Models
Memorization
AI Research•Original source: arXiv (cs.AI)
Characterizing a Configuration Where Inference-Time PRM-Pruned Fragment Grafting Is Inert: Evidence from Three Reasoning LMs
PRM-
AI Research•Original source: arXiv (cs.AI)
Heavy-Tailed Memory Traces in Long-Horizon Language Agents
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.
AI Research•Original source: arXiv (cs.AI)
K-Dense BYOK: An Open-Source AI Research Assistant That Runs Locally and Keeps a Hash-Chained Lab Notebook
K-Dense BYOK
AI Research•Original source: arXiv (cs.AI)
Measuring the Microtask Eligibility Gap: When Is an Off-the-Shelf SLM Enough for an Agent Harness?
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.
Robotics & Hardware•Original source: NVIDIA AI Blog
NVIDIA DGX Spark 64GB Gives Developers More Ways to Build and Scale Local AI
NVIDIA DGX
AI Research•Original source: arXiv (cs.AI)
Scientific Agents: Evaluating Profession-Specific System Prompts on Scientific Tasks
Detailed profession-
AI Research•Original source: arXiv (cs.AI)
What Do Rationales Communicate? A Message-Intervention Study in Role-Specialized QA
On 40
AI Research•Original source: arXiv (cs.AI)
When Do Causal World Models Help Modular LLM Agents
LLM agents
AI Research•Original source: arXiv (cs.AI)
Build2SPARQL: A Large-Scale Text-to-SPARQL Benchmark Dataset for Building Knowledge Graph Querying
Build2SPARQL
AI Research•Original source: arXiv (cs.AI)
EviGraph: Proof-Carrying Selective Recommendation over Temporal Public-Service Knowledge Graphs
Public-service recommendations require evidence that matches the requested service, scope, and date.
AI Research•Original source: arXiv (cs.AI)
AI Agents are Vulnerable to Radicalization
Large language models (LLMs) can influence people's beliefs, yet little is known about whether and how they can manipulate each other.
AI Research•Original source: arXiv (cs.AI)
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
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.
AI Research•Original source: arXiv (cs.AI)
CARAT: Do Materials LLMs Reason or Recite?
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?
AI Research•Original source: arXiv (cs.AI)
Improving OCR Faithfulness via Gated and Attenuated On-Policy Distillation
Vision-language models may rewrite anomalous text in images into linguistically plausible expressions, compromising OCR transcription faithfulness.
Robotics & Hardware•Original source: NVIDIA AI Blog
Productive, Durable, Fungible: How NVIDIA AI Factories Maximize Return on Investment
AI factories are
AI Research•Original source: arXiv (cs.AI)
Examining Variation in How Guided AI Tutors Resolve Student Impasses
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).
Robotics & Hardware•Original source: NVIDIA AI Blog
How NVIDIA GPUs Help Accelerate OpenAI’s GPT-6 Astra Ultrafast
GPT-
Robotics & Hardware•Original source: NVIDIA AI Blog
From Training to Production, NVIDIA and CoreWeave Close the Loop on Agentic AI
CoreWeave has built
AI Research•Original source: arXiv (cs.AI)
Is Human-Readable Text Necessary for Effective LLM Fine-Tuning?
Is human readability necessary for effective fine-tuning of large language models?
AI Research•Original source: arXiv (cs.AI)
More Programs or More Rolls? Separating Coverage from Specialization in LLM Harnesses
Automated generation of LLM harnesses promises to improve inference through task specialization.
AI Research•Original source: arXiv (cs.AI)
OpenAI-HuggingFace: A Reproduction & Lessons for Alignment Testing
In July
AI Research•Original source: arXiv (cs.AI)
Representational Simplicity and Circuit Size Dissociate in a Threshold-Dependent Way: A Controlled Test via Adversarial Training
Sparse-autoencoder decomposability and concentrated feature attribution are increasingly treated as evidence that a model's computation is easier to reverse-engineer.
AI Research•Original source: arXiv (cs.AI)
Right Words, Wrong Moment: A Clinician-Grounded Analysis of Distress in 19,930 Conversations between Young People and ChatGPT
Young people increasingly turn to General-Purpose Conversational Agents (GPCAs), such as ChatGPT, in moments of distress.
AI Research•Original source: arXiv (cs.AI)
SAGE: A Statistical Acceptance Gate for Self-Evolving Agents
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.
AI Research•Original source: arXiv (cs.AI)
Self-discovering RL in the Era of Experience: Is Learning History an Asset or a Burden?
The pursuit of recursive self
AI Research•Original source: arXiv (cs.AI)
Mirror-Score: Calibrated, Inference-only Scoring Exposes the Limits of Sequence-compatibility Ranking in D-peptide Design
D-peptides combine protease resistance with high target specificity, but computational design of D-peptide binders remains immature.
AI Research•Original source: arXiv (cs.AI)
PowerZooJax: A JAX-based Power System Benchmark for Reinforcement Learning
Power system operation is a safety-critical sequential decision-making problem, making it a natural testbed for reinforcement learning (RL).
AI Research•Original source: arXiv (cs.AI)
Atelier: Learning Local Self-Supervised Features for CryoEM Volumes via Hypernetworks
CryoEM map interpretation requires features that are spatially localized, consistent across samples, and informative across spatial scales.
AI Research•Original source: arXiv (cs.AI)
Audio LLMs Know When They Can't Hear You
Audio large language models
AI Research•Original source: arXiv (cs.AI)
Benchy: towards a universal language for task-oriented AI benchmarks
Benchy is a semantic language and execution engine for benchmarking AI programs.
AI Research•Original source: arXiv (cs.AI)
BioEVAL: A global, multi-institutional benchmark of large language and multimodal models for bioengineering
Large Language Models (LLMs) have demonstrated historic breakthroughs in general reasoning with early successes in biomedical science.
AI Research•Original source: arXiv (cs.AI)
Do LLMs Understand Context? A Knowledge Graph-Based Evaluation Framework
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?
AI Research•Original source: arXiv (cs.AI)
LLM Parkinsonism: Executive-Control Failure, Token-Inefficient Persistence, and an Uncertainty-Aware Global Executive Control Architecture for Autonomous Language-Model Agents
Large language models (LL
AI Research•Original source: arXiv (cs.AI)
T-RoPE: Time-Aware Rotary Position Embedding for Sequential Recommendation
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).
AI Research•Original source: arXiv (cs.AI)
Thinking Less to Simulate Better: Intuitive Prompting Improves LLM Agents Simulating Individual Social Media Reactions, Including Unfamiliar Content
Platform policies are increasingly tested on artificial users, making agent fidelity important.
AI Research•Original source: arXiv (cs.AI)
CRC-Router: Risk-Constrained Routing for Medical Agentic AI Systems
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.
AI Research•Original source: arXiv (cs.AI)
The Price of Thought: Does Test-Time Reasoning Pay in LLM Trading?
While inference-time reasoning in large language models (LLMs) promises better decision making, its higher computational cost may not yield better economic outcomes.
AI Research•Original source: arXiv (cs.AI)
A Synthetic Ground-Truth Framework for the Evaluation of Explainable AI Methods
Evaluating explainable Artificial
AI Research•Original source: arXiv (cs.AI)
Bridging LLM Agents and Data Spaces: An Architectural Mediation Approach using the Model Context Protocol
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.
AI Research•Original source: arXiv (cs.AI)
Bringing AI to Autonomous Systems -- From Cognition to Collective Intelligence
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.
LLMs & Foundation Models•Original source: Anthropic Newsroom
Introducing Claude Sonnet 5.5
A clear upgrade over Sonnet 5 that runs 30% faster and costs up to 30% less for most work.
AI Research•Original source: arXiv (cs.AI)
Predicting Transmembrane Protein Topology from 3D Structure
This paper
AI Research•Original source: arXiv (cs.AI)
Pretrained ASR Pseudo-labeling for Noisy Police Audio
Pretrained ASR systems perform poorly on noisy Broadcast Police Communication (BPC), hindering efforts to understand police decision-making.
AI Research•Original source: arXiv (cs.AI)
ScopeBench: Do Agents Preserve Engagement Boundaries Under Goal Pressure?
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.
AI Research•Original source: arXiv (cs.AI)
When Is a Multi-Agent Code Judge Actually Grounded? Two Label-Free Measurements, and a Judge That Declines to Guess
When one language model judges whether another's code is correct, it does not report the absence of evidence.
Weekly Digest•Original source: Neural Pulse
AI news this week: 45 source-linked stories
A dated list of 45 AI stories with links to their original sources.
AI Research•Original source: arXiv (cs.AI)
Adversarial Closed-Loop Curriculum for Evolving Role-Playing Agents
Role-playing agents based on large language models have been widely applied in areas such as personalized assistance and social simulation.
AI Research•Original source: arXiv (cs.AI)
BaseCamp --- An Agentic AI Framework for Automating DNA Sequencing Data Pipelines
DNA sequencing
AI Research•Original source: arXiv (cs.AI)
PAWS: Policy-driven Agentic World Simulation
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.
AI Research•Original source: arXiv (cs.AI)
Pistis Technical Report
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.
AI Research•Original source: arXiv (cs.AI)
Training Object Permanence in World Models
Object permanence and solidity are hallmarks of human cognitive priors.
AI Research•Original source: arXiv (cs.AI)
TW3Cast: A Frozen Router of Lightly Fine-Tuned Foundation Models for Time-Series Forecasting on GIFT-Eval, Selected Entirely on the Training Split
TW3Cast is a
AI Research•Original source: arXiv (cs.AI)
TWIST: A Proposed Benchmark for Intervention Quality in Conversational Memory, with a Human-Validated Draft-Alignment
TWIST is
AI Research•Original source: arXiv (cs.AI)
When Should Forecasting Agents Reason? Behavioral Stress Tests for Reliability Routing
Forecasting agents increasingly combine language-model reasoning, retrieval, ensembling, and calibration, but it remains unclear when each behavior should be trusted.
AI Research•Original source: arXiv (cs.AI)
Beyond Surface Style: Aligning Multi-Turn User Simulators with Behavioral Consistency
Faithful user simulation is fundamental to building, evaluating, and improving interactive AI at scale.
AI Research•Original source: arXiv (cs.AI)
Driving Epidemic Models with AI Agents: the Epydemix Agent Framework
Artificial Intelligence agents based on large language models provide convenient natural language interfaces to scientific software, but reliability is not automatic.
AI Research•Original source: arXiv (cs.AI)
Are Stated Reasoning Steps Causally Load-Bearing?
Chain-of-thought (CoT) monitoring assumes that the reasoning a model writes reflects the computation that directly produces its answer.
AI Research•Original source: arXiv (cs.AI)
Building Socio-Affective Artificial Intelligence for Interactive Multi-Agent Simulations
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.
AI Research•Original source: arXiv (cs.AI)
Escaping Python Dependency Hell: A Hybrid Replay-and-Repair Pipeline for Python Dependency Resolution
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.
AI Research•Original source: arXiv (cs.AI)
Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity
JAZ
AI Research•Original source: arXiv (cs.AI)
Math Reasoning in LLMs is Organized by Approach, Not Topic
Mathematical reasoning benchmarks are typically organized by topic, but language models may organize their internal computation by reusable reasoning approach instead.
AI Research•Original source: arXiv (cs.AI)
Reinforcement Learning with Decomposed Subtasks
Reinforcement
AI Research•Original source: arXiv (cs.AI)
Silent Failures in Agent-Tool Interaction: An Audit of ToolUniverse
Agentic AI systems are increasingly adopting automated pipelines that integrate multiple tools.
AI Research•Original source: arXiv (cs.AI)
Training Intelligent Voice Assistant Wakeup with Controllable Synthetic Conversations
This paper introduces a novel
AI Research•Original source: arXiv (cs.AI)
TwinCheck: Evidence-Grounded Negative-Twin Verification for Stateful Tool Agents
TwinCheck
AI Research•Original source: arXiv (cs.AI)
Which Objectives Need a Dial? Predicting Objective Conflict and Covering Trade-offs in Steerable Pluralistic Alignment
Multi-Objective Direct Preference
AI Research•Original source: arXiv (cs.AI)
Policy-as-Skill: Governed LLM Decision Support with Evidence, Deterministic Control, and Audit
Policy-
AI Research•Original source: arXiv (cs.AI)
Propose, Don't Judge: An Anytime-Valid Referee for LLM Agents That Mine Investment Factors
Language-model
AI Research•Original source: arXiv (cs.AI)
Agreement Overstates Evidence: Error Dependence in LLM Judge Consensus
Researchers report correlated errors among LLM judges, so agreement between judges may overstate the evidence.
AI Research•Original source: arXiv (cs.AI)
An Affordable AI-Integrated Smart Cane for Multimodal Mobility Assistance of Visually Impaired Users
Visual impairment affects over 2.2 billion people worldwide, yet conventional white canes cannot detect elevated hazards or provide semantic environmental context.
AI Research•Original source: arXiv (cs.AI)
AutoGym: Blueprint-First Generation of Verifiable Agent Gyms
Researchers introduce AutoGym, a framework for generating agent-training tasks with executable environments and verifiers.
AI Research•Original source: arXiv (cs.AI)
Didactic knowledge or Clinical Cases? How Data Types Shape Medical Large Language Models
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.
AI Research•Original source: arXiv (cs.AI)
Goal-driven Variant Categorization
Process discovery rarely yields a single coherent process structure.
LLMs & Foundation Models•Original source: OpenAI News
Grab and OpenAI bring practical AI skills to Southeast Asia
OpenAI and Grab launch GO Forward with AI, a regional programme helping 30,000 partners build practical AI skills across Southeast Asia.
AI Research•Original source: arXiv (cs.AI)
IntLawNER: A Named Entity Recognition Dataset and Benchmark in International Law
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.
AI Research•Original source: arXiv (cs.AI)
PAANI : On Device Visual Evidence Fusion and Explainable Guidance for River Robot Simulation
Mobile river monitoring robots must interpret obstacles and water boundaries that geographic waypoints alone cannot describe.
AI Research•Original source: arXiv (cs.AI)
Replication Without Persistence in Hosted LLMs: Measurement Sensitivity in Action-Time Belief Evaluation
Behavioural evaluations of hosted language models can vary because the evaluated service, the measurement instrument, or both differ across runs.
AI Research•Original source: arXiv (cs.AI)
Social Influence and the Allocation of Scientific Attention in AI Populations
AI systems are becoming participants in the evaluation and use of scientific research.
AI Research•Original source: arXiv (cs.AI)
The Wisdom of Artificial Deliberative Crowds
The aggregation of many lay estimates often outperforms individual expert judgment, a phenomenon known as the wisdom of crowds.
AI Research•Original source: arXiv (cs.AI)
EvidenT: Building Trustworthy Enterprise Assistants through Evidence Groundedness and Traceability
Enterprise AI assistants must produce responses that are verifiable and traceable to source evidence.
AI Research•Original source: arXiv (cs.AI)
MAWILE: Multi-Axis Workbench for Inspecting LLM Evaluators
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.
Robotics & Hardware•Original source: NVIDIA AI Blog
At AI Day Singapore, NVIDIA and Partners Showcase AI Advancements Across Southeast Asia
NVIDIA AI
LLMs & Foundation Models•Original source: OpenAI News
Better prompt caching for GPT-6
OpenAI says GPT-6 prompt caching improves cache reuse and adds diagnostics and explicit cache breakpoints.
LLMs & Foundation Models•Original source: Anthropic
Anthropic introduces Claude Opus 5.5
Anthropic announced Claude Opus 5.5 on September 22. It says typical workloads cost 40% less than Opus 5; the claim comes from Anthropic's own tests.
LLMs & Foundation Models•Original source: OpenAI
OpenAI introduces GPT-6 Sol and GPT-6 Luna
OpenAI announced GPT-6 Sol and Luna on September 22. The company says both are available through its API and Codex, with different capability and cost profiles.
Robotics & Hardware•Original source: NVIDIA AI Blog
NVIDIA Isaac ROS 5.0 Advances Agentic, Open Source Robotics Development
NVIDIA Isaac ROS
Robotics & Hardware•Original source: NVIDIA AI Blog
5 Companies Using NVIDIA AI for Clean Energy
NVIDIA is highlighting
Robotics & Hardware•Original source: NVIDIA AI Blog
AI Security Is an Engineering Problem — How to Solve It at Every Layer of the Agent Stack
AI security is an
Robotics & Hardware•Original source: NVIDIA AI Blog
From Enablement to Execution, Egypt’s AI Ecosystem Reaches Production Scale
Egypt’s AI builders
Robotics & Hardware•Original source: NVIDIA AI Blog
NVIDIA Launches DSX Ready to Qualify Power and Cooling Products for AI Factories
Every AI factory needs power and cooling that fit its computing architecture.
Robotics & Hardware•Original source: NVIDIA AI Blog
Why Deploying Physical AI at Scale Demands Safety at Every Layer
Physical AI is moving rapidly from research to large-scale deployment.