Post-training has become central to turning pretrained large language models (LLMs) into aligned and deployable systems. Recent progress spans supervised fine-tuning (SFT), preference optimization, reinforcement learning (RL), process supervision, verifier-guided methods, distillation, and multi-stage pipelines. Yet these methods are often discussed in fragmented ways, organized by labels or objective families rather than by the behavioral bottlenecks they address. This survey argues that LLM post-training is best understood as structured intervention on model behavior. We organize the field first […]

Ver mais

I’ve spent the better part of my career designing database architectures for systems that genuinely cannot go down. Finance platforms. Healthcare workflows. The kind of systems where a 90-second outage shows up in a board meeting two weeks later. In that time, I’ve run SQL Server and PostgreSQL side by side across enough production environments to have real opinions about both and one of the clearest findings is that the gap between them in high availability setups is […]

Ver mais

Class-incremental learning (CIL) with pre-trained models (PTMs) faces a critical trade-off between efficient adaptation and long-term stability. While analytic learning enables rapid, recursive closed-form updates, its efficacy is often compromised by accumulated errors and feature incompatibility. In this paper, we first conduct a systematic study to dissect the failure modes of PTM-based analytic CIL, identifying representation rigidity as the primary bottleneck. Motivated by these insights, we propose textbf{VILA}, a novel dual-branch framework that advances analytic CIL via a […]

Ver mais

Agentic Engineering Patterns > I use the term agentic engineering to describe the practice of developing software with the assistance of coding agents. What are coding agents? They’re agents that can both write and execute code. Popular examples include Claude Code, OpenAI Codex, and Gemini CLI. What’s an agent? Clearly defining that term is a challenge that has frustrated AI researchers since at least the 1990s but the definition I’ve come to accept, at least in the field […]

Ver mais

arXiv:2602.17692v1 Announce Type: new Abstract: In this paper, we introduce textbf{agentic unlearning} which removes specified information from both model parameters and persistent memory in agents with closed-loop interaction. Existing unlearning methods target parameters alone, leaving two critical gaps: (i) parameter-memory backflow, where retrieval reactivates parametric remnants or memory artifacts reintroduce sensitive content, and (ii) the absence of a unified strategy that covers both parameter and memory pathways. We present Synchronized Backflow Unlearning (SBU), a framework that unlearns jointly […]

Ver mais

Accurate representation of multimodal knowledge is crucial for event forecasting in real-world scenarios. However, existing studies have largely focused on static settings, overlooking the dynamic acquisition and fusion of multimodal knowledge. 1) At the knowledge acquisition level, how to learn time-sensitive information of different modalities, especially the dynamic structural modality. Existing dynamic learning methods are often limited to shallow structures across heterogeneous spaces or simple unispaces, making it difficult to capture deep relation-aware geometric features. 2) At the […]

Ver mais

arXiv:2602.06098v1 Announce Type: new Abstract: Coding agents are increasingly utilized in test-driven software development, yet the theoretical mechanisms behind their environment-interaction strategies remain underexplored. We provide a probabilistic framework for two dominant paradigms: code selection after generation using the execution environment, and code generation conditioned on environment feedback. First, we formalize several well-established selection heuristics as environment-aware estimators of code correctness. We theoretically prove that estimators based on fuzzy functional similarity add an inductive bias and strictly dominate […]

Ver mais

arXiv:2509.19988v2 Announce Type: replace Abstract: Efficient design of genomic perturbation experiments is crucial for accelerating drug discovery and therapeutic target identification, yet exhaustive perturbation of the human genome remains infeasible due to the vast search space of potential genetic interactions and experimental constraints. Bayesian optimization (BO) has emerged as a powerful framework for selecting informative interventions, but existing approaches often fail to exploit domain-specific biological prior knowledge. We propose Biology-Informed Bayesian Optimization (BioBO), a method that integrates Bayesian […]

Ver mais