Daily report — 2026-10-14

Gaussian process bandits exploit similarities among configurations to optimize prompts, retrieval systems, and agent workflows. In these applications, however, inexpensive model-based evaluations can disagree with trusted task outcomes.

Claimed: none extracted

Evidence: + toy/synthetic experiments ("Synthetic"); + small/synthetic data ("Synthetic"); + explicit algorithm/pseudocode ("Algorithm 1"); + formal statement ("bound"); no public code found; + keywords: retrieval, kernel, bandit

heuristic

Large language models can answer the same question in different styles, but users' preferred styles are hidden and vary across users and questions. We study inference-time personalization through online selection from a fixed set of prompts, each representing a persona.

Claimed: none extracted

Evidence: - LLM-based ("LLM"); + toy/synthetic experiments ("simulated"); + small/synthetic data ("simulated"); + public benchmarks ("benchmark"); + concrete method ("closed form"); + formal statement ("bound"); + claims simplicity ("simple"); + code: https://github.com/RoGy-Labs/tutorduel-code; + keywords: bandit

heuristic

Bayesian predictive regions account for parameter uncertainty but can be poorly calibrated under model misspecification, even with expensive full MCMC. Cheaper approximations such as variational inference reduce the cost but often yield less accurate predictive distributions.

Claimed: none extracted

Evidence: + toy/synthetic experiments ("simulations"); + small/synthetic data ("simulated"); + public benchmarks ("benchmarks"); + explicit algorithm/pseudocode ("Algorithm 1"); + formal statement ("bound"); no public code found; + keywords: monte carlo, variational

heuristic

Persistent homology summarizes the topological evolution of a graph as persistence diagrams (PDs). Generating graphs whose topology matches a target descriptor is increasingly important, yet existing topology-aware generative models rely on soft regularization, producing graphs whose PDs may only be approximately similar.

Claimed: none extracted

Evidence: + public benchmarks ("benchmarks"); + explicit algorithm/pseudocode ("Algorithm 1"); + formal statement ("we prove"); + claims simplicity ("simple"); + code: https://github.com/Aalto-QuML/ExactCompliance; + keywords: regularization

heuristic

We develop a comprehensive theoretical analysis of Matrix Shampoo for tracking time-varying optima in nonstationary stochastic optimization. We derive finite-horizon high-probability bounds for average tracking error that disentangle initialization, optimizer drift, momentum-induced drift penalty, stochastic noise, and adaptive preconditioning, with explicit dependence on momentum parameter \(β_1\

Claimed: none extracted

Evidence: + toy/synthetic experiments ("synthetic"); + small/synthetic data ("synthetic"); + explicit algorithm/pseudocode ("Algorithm 1"); + formal statement ("bound"); no public code found; + keywords: optimizer

heuristic

Autonomous research agents must acquire and reason over evidence within a limited budget. Yet relevant sources can remain uninspected or unused, leaving a gap between retrieval coverage and the evidence that informs research.

Claimed: none extracted

Evidence: + formal statement ("bound"); + code: https://github.com/sunyasheng/JevGPT; + keywords: retrieval, ranking; + 6 HF upvotes

heuristic

Evaluating recommender systems before deployment requires simulators that remain realistic over long, closed-loop interaction cycles. Current LLM-based agents generally function as surface imitators that generate realistic short-term responses but fail to capture the underlying user dynamics such as fatigue, affect, and shifting preferences.

Claimed: none extracted

Evidence: - LLM-based ("LLM"); + toy/synthetic experiments ("simulated"); + CPU-friendly ("lightweight"); + small/synthetic data ("simulated"); + public benchmarks ("Benchmark"); - system/framework (many moving parts) ("framework"); + code: https://github.com/franz-chang/PsyBer-Agent; + 4 HF upvotes

heuristic

Simulation-based Bayesian inference for Chemical Reaction Networks (CRNs) must simultaneously solve two computationally demanding problems: discriminating between overlapping reaction pathways and estimating reaction rate constants. Classical approaches, such as Sequential Monte Carlo ABC, rely on handcrafted summary statistics and scale poorly across large parameter spaces.

Claimed: none extracted

Evidence: + toy/synthetic experiments ("Simulation"); + formal statement ("theorem"); + code: https://github.com/Esquivel-Arturo/JNPE; + keywords: monte carlo

heuristic

Evaluating fashion retrieval systems remains challenging due to the limited availability of benchmarks that capture the fine-grained, open-ended queries encountered in real-world search and recommendation. Existing benchmarks often rely on manual curation, predefined taxonomies, or synthetic prompts, limiting scalability and semantic coverage.

Claimed: none extracted

Evidence: + toy/synthetic experiments ("synthetic"); + small/synthetic data ("synthetic"); + public benchmarks ("benchmarks"); - system/framework (many moving parts) ("framework"); no public code found; + keywords: retrieval, variational, ranking

heuristic

We present SWE-MISBEHAVIOR, the first taxonomy and evaluation framework for diagnosing boundary-violating misbehaviors in coding agents. It contains 7.4K human-in-the-loop synthesized samples spanning three layers of agent action space: (i) Code Generation, (ii) File Management, and (iii) System Interaction.

Claimed: none extracted

Evidence: + CPU-friendly ("lightweight"); - system/framework (many moving parts) ("framework"); + code: https://github.com/dxlong2000/SWE-Misbehavior; + 5 HF upvotes

heuristic