The daily ledger

How to Build Bug-Free Applications with Claude Code

Use E2E tests to minimize bugs The post How to Build Bug-Free Applications with Claude Code appeared first on Towards Data Science.

We Taught AI to Answer Questions. Who Taught It to Change Its Mind?

When new evidence kills one conclusion, do the decisions built on it change too? I tested six update strategies, then a local model. The post We Taught AI to Answer Questions. Who Taught It to Change Its Mind? appeared…

I Told an AI Agent That Its Wrong Answers Were Right. One Model Believed Me.

A research paper claims reward labels barely change how agents learn. I tested that on three models, and one of them did exactly what the wrong labels told it to. The post I Told an AI Agent That Its Wrong Answers Were…

The Neuron Academy - Dedicated Send - 10.31.26

"Close enough?" An investigation into multiplication errors in LLMs

arXiv:2610.38634v1 Announce Type: new Abstract: Large language models (LLMs) frequently fail at multi-digit arithmetic, but the underlying mechanisms governing these failures remain poorly understood. While recent work…

Generative Interactions: Weaving Multiparty Human Motion with Bilevel Latent Dynamics

arXiv:2609.37708v2 Announce Type: replace Abstract: Human social behaviour is not a collection of independent motions, but a jointly organised process in which group dynamics and individual variation continuously shape…

One Confidence Threshold, Unequal Coverage: Language Gaps in Typed Decision Interfaces and How Translating Inputs Reduces Them

arXiv:2610.37688v1 Announce Type: cross Abstract: Deployed classifiers often act on a prediction only when its confidence clears a threshold and pass the rest to a person. We ask whether one threshold serves all…

Scan Before You Install: Detecting and Mitigating Local and Composite Vulnerabilities in Skills

arXiv:2610.37901v1 Announce Type: cross Abstract: An agent skill packages natural-language instructions, scripts, and reference files that an LLM-based agent loads for a task. Skills may access the file system, shell,…

Locating and Closing Information Gaps in Multi-Agent Systems

arXiv:2610.40186v1 Announce Type: new Abstract: Multi-step Web tasks often require several LLM agents to gather and combine evidence. The communication graph of a fixed workflow restricts which agents can read each…

Understanding axial attention in TSFMs through single location regression

arXiv:2610.40188v1 Announce Type: cross Abstract: Recent advances in Time Series Foundation Models (TSFMs) increasingly rely on axial attention mechanisms, but despite their empirical success, the theoretical properties…

Verifiable LLM-Guided Focal SMT Solving for Quantified Arrays

arXiv:2610.39435v1 Announce Type: new Abstract: Large language models can often identify useful semantic structure in formal artifacts, but their outputs cannot be trusted as proofs or solver decisions. We study whether…

ClueTracer: Question-to-Vision Clue Tracing for Training-Free Hallucination Suppression in Multimodal Reasoning

arXiv:2602.02004v2 Announce Type: replace-cross Abstract: Large multimodal reasoning models solve challenging visual problems via explicit long-chain inference: they gather visual clues from images and decode clues into…

DeFT-RAG: Incrementally Decomposing Multi-Hop Questions into Self-Contained Sub-Questions with Reusable Answers

arXiv:2610.37826v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) lets a large language model (LLM) answer questions by retrieving relevant passages from a large corpus. However, RAG struggles with…

TaskFrame: Connecting Task-Level Planning with Frame-Level Control for Game Agents

arXiv:2610.40276v1 Announce Type: cross Abstract: Building general game agents requires both high-level task reasoning and low-latency action control in rapidly changing visual environments. These capabilities favor…

Artifact Distillation: Training-Free Transfer from Frontier to Small Language Models

arXiv:2610.37680v1 Announce Type: cross Abstract: Closing the gap between frontier and smaller language models is usually approached by distillation: fine-tuning the small model (student) on a frontier model's (teacher)…

Benchmarking Graph Neural Networks for AC Power Flow: The Role of Inductive Biases and Physical Constraints

arXiv:2610.38985v1 Announce Type: cross Abstract: Fast and accurate models for AC power flow (ACPF) are increasingly important as modern electrical grids require more frequent system analyses. Graph neural networks…

SaiVLA-JEPA: Evaluating Future Latent Prediction in JEPA-Conditioned VLA Control

arXiv:2610.38508v1 Announce Type: cross Abstract: Joint-embedding predictive architectures (JEPAs) learn to predict representations rather than pixels, offering a compact way to model how visual scenes evolve. We ask…

WebAnything: From the Wild Web to Scalable Agent Environments

arXiv:2610.37786v1 Announce Type: new Abstract: Web agents require diverse, executable, and resettable website environments for reproducible training and evaluation. Human-assisted mirrors demand per-site engineering,…

Raincheck: Deferred Multimodal Prefill for Efficient Multi-Turn MLLM Inference

arXiv:2610.39562v1 Announce Type: cross Abstract: Multi-turn conversations with multimodal large language models (MLLMs) reuse input context, but long multimodal inputs increase time to first token (TTFT). Query-aware…

From Leniency to Suspicion: How an Open Post-Training Recipe Changes Whom LLM Fact-Checkers Believe

arXiv:2610.38532v1 Announce Type: new Abstract: LLMs increasingly fact-check online content with the poster's identity in view. However, it remains unclear which post-training changes how much a model's truth judgement…