arbor adds tree search as cognition layer for ai agents
arbor introduces structured tree search as a shared working memory for multi-agent systems, improving autonomous optimization in complex, stateful environments.
aitag research
summaries filed under research
toolsense audits llm tool knowledge
a new framework tests if language models truly understand the tools they retrieve, not just match patterns.
aiepistemic uncertainty is not always reducible
new research shows that the standard definition of epistemic uncertainty as reducible by more data is inconsistent with its common mutual-information measure, and proposes a three-part taxonomy.
aigoogle deepmind launches $10m multi-agent ai safety fund
google deepmind and partners announce a $10m research call to study safety risks when many ai agents interact.
aiclaude fable is relentlessly proactive
simon willison describes how claude fable 5 autonomously debugged a ui glitch by inventing browser automation tricks, raising safety concerns.
aillm pipeline automates pre-mediation for human negotiation
a structured llm pipeline supports pre-mediation in integrative negotiation, improving agreement rates and joint outcomes in human experiments.
aiconformal bayes under label shift
two approaches for conformal bayes under label shift: post-hoc calibration and in-training adaptation, both using importance weighting to restore target-domain coverage.
aiai agents struggle to synthesize scientific conclusions
a new benchmark reveals that even top ai models produce low-quality factual summaries from scientific evidence, with the best achieving only 0.33 f1 score.
aisteering away from sycophancy also cuts factual agreement
activation steering meant to reduce sycophancy in language models also lowers agreement with true statements, showing a structural overlap that current methods cannot separate.
aiannealed entropic allocation for ranking and selection
a new annealed weighted soft-min framework improves sequential budget allocation in ranking and selection by smoothing the maximin objective and adding saddlepoint corrections.
aijeremy howard on slowing recursive ai self-improvement
jeremy howard argues that if a lab wants to slow frontier ai progress, it should not use its own top model for that research, while others should have access.
aigoogle deepmind launches robotics accelerator for european startups
google deepmind selects 15 robotics startups for a three-month program offering mentorship and ai tools to build real-world applications.
aitopological features as survival data for testing and learning
a new method treats persistence diagrams as survival data, enabling hypothesis testing, effect sizes, and stable feature vectors for machine learning.
aiprohiflo: hierarchical flow matching for protein generation
a new hierarchical flow matching framework generates proteins with functional guidance and fewer sampling steps.
aiboltzmann margin gives knn near-exponential convergence
a new margin condition bridges the gap between polynomial and exponential rates for knn classifiers.
aihow audio and visual signals flow through multimodal llms
a study traces how audio-visual large language models route and integrate sensory information, revealing task-dependent pathways and a shift in routing for interleaved inputs.
ainew framework for auditing machine unlearning
google research introduces regularized f-divergence kernel tests to verify machine unlearning with higher sensitivity and fewer samples.
aipredictive ai compresses search before exploration
a geometric model shows how predictive ai stabilizes problem-solving trajectories early, reducing exploratory diversity and potentially trapping users in narrow strategy regions.
aimemory tools can make ai models worse
new research shows that ai memory systems can degrade model accuracy by amplifying user misconceptions and irrelevant preferences.
aidiffusiongemma speeds up local text generation 4x
google deepmind releases an experimental open model that generates text in parallel blocks, achieving up to 4x faster inference on dedicated gpus.
ai