arXiv:2609.38346v1 Announce Type: new Abstract: When a student is stuck, a tutor faces the assistance dilemma: help given too early can hinder productive…
Aligned Data Can Induce Misalignment via Context Confusion
arXiv:2609.38379v1 Announce Type: new Abstract: Large language models (LLMs) are frequently updated for various use cases, where filtering out misaligned…
Beyond Mode Collapse: Generating Diverse Synthetic Expert Conversations via Generative Flow Networks
arXiv:2609.38359v1 Announce Type: new Abstract: High quality synthetic data is central to post training LLMs for adaptive AI applications that represent…
Self-Evolving Harness on Multiple Tasks with the Agent as Its Own Optimizer
arXiv:2609.38372v1 Announce Type: new Abstract: A harness is the code around a language-model agent that organizes prompts, calls tools, manages context,…
Can an AI Agent Rediscover a Blaschke-Curve Invariant?
arXiv:2609.38369v1 Announce Type: new Abstract: We study generalized Blaschke curves as a controlled environment for AI-assisted mathematical rediscovery.…
MoFlow: Multi-Objective Agentic Workflow Generation
arXiv:2609.38294v1 Announce Type: new Abstract: We study the generation of agentic workflows that jointly optimize multiple objectives, such as accuracy,…
AI Agents are Vulnerable to Radicalization
arXiv:2609.38296v1 Announce Type: new Abstract: Large language models (LLMs) can influence people’s beliefs, yet little is known about whether and how…
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
arXiv:2609.38288v1 Announce Type: new Abstract: We present AREX-2, an effort to advance the self-improving capability of LLM agents, which we define as…
Improving OCR Faithfulness via Gated and Attenuated On-Policy Distillation
arXiv:2609.38282v1 Announce Type: new Abstract: Vision-language models may rewrite anomalous text in images into linguistically plausible expressions,…
CARAT: Do Materials LLMs Reason or Recite?
arXiv:2609.38340v1 Announce Type: new Abstract: When a materials LLM answers a question about crystal structure, does it reason from the structure or copy…
AI News Brief Hourly Summary 2026-10-01 06h : 12 posts
12 posts published in the last hour 03:32Estimation of Room Impulse Responses from Handclaps 03:32Position: Let’s Strengthen Verifiability If We Can’t Enforce Reproducibility 03:32When Should LLMs Trust Their Own Revisions? A Risk-Aware Study of Intrinsic Self-Correction 03:32Mara Chain: Rethinking Failure…
Estimation of Room Impulse Responses from Handclaps
arXiv:2609.35839v1 Announce Type: cross Abstract: Handclaps provide an equipment-free excitation for room acoustics, but their unknown and variable source…
Position: Let’s Strengthen Verifiability If We Can’t Enforce Reproducibility
arXiv:2609.35854v1 Announce Type: cross Abstract: In the field of Machine Learning, many papers contain empirical results supporting claimed statements or…
When Should LLMs Trust Their Own Revisions? A Risk-Aware Study of Intrinsic Self-Correction
arXiv:2609.35832v1 Announce Type: cross Abstract: Intrinsic self-correction asks a language model to revise its own answer without receiving new external…
Mara Chain: Rethinking Failure as a Stepping Stone for AI System Auto-Evolution
arXiv:2609.35855v1 Announce Type: cross Abstract: Optimizing deployed AI systems increasingly amounts to editing prompts, skills, harnesses, and code…
Perplexity Releases pplx-embed-v2-context-9b-preview: A Contextual Embedding Model That Retrieves Answers and Their Supporting Evidence
Perplexity Research and turbopuffer have released pplx-embed-v2-context-9b-preview, a contextual embedding model for RAG pipelines. Each chunk is embedded…
Beyond Rule-Based Mutation Testing: Test-Aware Mutant Generation Using Large Language Models
arXiv:2609.35841v1 Announce Type: cross Abstract: Mutation testing evaluates test-suite adequacy by injecting synthetic faults into program code. However,…
Constructing Challenging Browser-Use Tasks by Controlled Environment Interventions
arXiv:2609.35814v1 Announce Type: cross Abstract: As browser-use agents improve, benchmarks keep pace by collecting new tasks, websites, and applications,…