An MIT expert committee warns that AI is eroding key parts of the college experience: office hours, study groups, and the school’s flagship research…
RASPER: Reward-Aligned Summarization of Clinical Notes for EHR Outcome Prediction
arXiv:2610.02979v1 Announce Type: new Abstract: Unstructured discharge notes in Electronic Health Records (EHRs) often carry signal complementary to…
AI Is Already Smarter Than Your Doctor. That’s Not the Scary Part.
I wanted AI to solve this problem. For years, I had been taking complicated patient histories, laboratory findings, symptoms, medications, supplements and…
DyadMem: A Long-Term Memory Benchmark of How Agents Work with Users
arXiv:2610.03020v1 Announce Type: new Abstract: Long-term agents must remember not only what is true about a user, but also how a particular agent should…
AI News Brief Hourly Summary 2026-10-05 14h : 11 posts
11 posts published in the last hour 11:32Reasoning with Evidence, Not Merely Rationales: Verifiable Preference Proofs for LLM-Based Recommendation 11:32CreateScore: Domain-Theory-Informed Bayesian Routing for LLM-Based CV Screening 11:32Continual Graph Memory for Mathematical Research Agents 11:32Relevant Evidence Decoding for Audio-Visual Hallucination…
Reasoning with Evidence, Not Merely Rationales: Verifiable Preference Proofs for LLM-Based Recommendation
arXiv:2610.02968v1 Announce Type: new Abstract: Large language models (LLMs) can infer user preferences from interaction histories and reviews, yet the…
CreateScore: Domain-Theory-Informed Bayesian Routing for LLM-Based CV Screening
arXiv:2610.02972v1 Announce Type: new Abstract: Large language models (LLMs) can support rubric-based screening of CVs, but applying a high-capability…
Continual Graph Memory for Mathematical Research Agents
arXiv:2610.02945v1 Announce Type: new Abstract: Using frontier agent harnesses to tackle mathematical research problems has emerged as an effective means…
Relevant Evidence Decoding for Audio-Visual Hallucination Mitigation
arXiv:2610.02976v1 Announce Type: new Abstract: Audio-Visual Large Language Models (AV-LLMs) remain prone to cross-modal hallucinations, where one…
Reliable Self-Evolution with Imperfect Proxy Rewards
arXiv:2610.02975v1 Announce Type: new Abstract: Large language model (LLM)-based self-evolving search is a promising approach to scientific discovery.…
LUMOS: Tracing Parametric Knowledge from Training Data to Behavioral Outputs in LLMs
arXiv:2610.02902v1 Announce Type: new Abstract: Current analyses of LLMs’ parametric knowledge are largely output-centric, drawing conclusions about what…
HASTE: Evolving Agent Harnesses Against Emerging Attacks Using Sparse Evidence
arXiv:2610.02920v1 Announce Type: new Abstract: Agent harnesses play a critical role in defenses by enforcing safety constraints to prevent unsafe…
Positive-Unlabeled Learning for Agent Safety False Alarm Auditing
arXiv:2610.02925v1 Announce Type: new Abstract: Safety monitors help safeguard language-model agents interacting with external tools and environments, but…
Frequency Is Not Sensitivity Identifying Safety-Sensitive Experts in Sparse MoE LLM
arXiv:2610.02910v1 Announce Type: new Abstract: Suppressing a small set of routed experts can weaken the safety behavior of a sparse Mixture-of-Experts…
When to Compile a Computer-Use Agent? Measuring Payback and Making Compilation Decisions for Token Efficiency
arXiv:2610.02932v1 Announce Type: new Abstract: Compiling GUI procedures that agents execute repeatedly into programs can reduce their token costs.…
AI News Brief Hourly Summary 2026-10-05 13h : 15 posts
15 posts published in the last hour 10:32Bounded Reachability & Jailbreak Detection via Contraction-Constrained State Space Models 10:32Interpreting at Write Time: A Policy Ablation for Multi-Goal Agent Memory 10:32Building advertising for the way people use AI 10:32TACD: Distilling Efficient Text-to-Motion…
Bounded Reachability & Jailbreak Detection via Contraction-Constrained State Space Models
arXiv:2610.02853v1 Announce Type: new Abstract: Safety heads are lightweight classifiers attached to pretrained language models for flagging harmful…
Interpreting at Write Time: A Policy Ablation for Multi-Goal Agent Memory
arXiv:2610.02897v1 Announce Type: new Abstract: A long-running assistant cannot keep everything it has seen, so it summarises. Summarising is not neutral:…