Developer & Engineering Blogs
Deep-dives, architecture logs, and research publications directly from leading AI labs and engineering hubs.
Benchmarking Language Models for Statistical Problem Formulation
Large language models (LLM) are increasingly used as assistants for statistical and data science work, yet existing evaluations largely assume the analysis...
ASCII Attack: Recontextualising Harmful Requests as Artistic Critique in Large Language Models
Safety alignment trains large language models to refuse harmful requests stated plainly, but that training is applied mostly to surface form. Requests that...
LLM-as-a-Judge Is Not an Oracle: Why Self-Improving Agents Need Deterministic Guardrails
Self-improving agent pipelines have a problem at their center. An optimizer rewrites prompt to score higher, and the score comes from a judge that is itself...
Architecting Conversational Data Systems for Stateless LLM APIs: The Hydration Proxy Pattern
As enterprise platforms transition to conversational reasoning interfaces, the stateless nature of LLM APIs creates an architectural gap. While statelessness...
Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems
Adapting the communication topology of an LLM multi-agent system to each query improves both accuracy and efficiency, yet current designers treat this as...
Epistemic Sybil Resistance: Multiplying AI Agents Without Multiplying Evidence
Multi-agent AI systems improve inference by spawning agents and synthesizing reports. But another agent is not another observation: apparently independent...
MASkills: Continual Skills Optimization for Multi-Agent LLM Systems
LLM-based multi-agent system have shown strong performance on complex tasks, yet continual improvement from interaction experience remains challenging...
Examining the Vulnerability of Multi-Agent Medical Systems to Human Interventions for Clinical Reasoning
Human interventions at fault points can alter the diagnostic accuracy of multi-agent medical systems. We defined fault points as moments in AI agent...
Beyond Outcome Gaps: Process-Aware Fairness Diagnosis for LLM-based Multi-Agent Decision Systems
LLM-based multi-agent system (MAS) are increasingly considered for high-stakes decision-making, yet outcome-based fairness audits can miss where risks arise...
CHIME: Credit-Aware Hierarchical Memory Evolution for Long-Horizon Agentic Planning
Planning is a central capability that enables agents to decompose complex long-horizon tasks into manageable steps. Test-time search and training-based...
CoMerge: Conflict-Driven Preference Optimization for Multi-Task Model Merging
Model merging provides an efficient paradigm for constructing multi-task large language models (LLM) without full model retraining, yet it remains...
FUSE: An Evaluating Framework for Dangerous Capabilities of LLMs
Fragmented safety evaluation undermines the governance of dangerous AI capabilities. We present a modular framework that evaluates each model through three...
Belief-Calibrated Optimization: An Explicit World Model for Agentic Optimization
The performance of an LLM agent depends on the scaffold around a frozen model. A common way to improve that scaffold is to use a coding agent as an...
PGPO: Potential-Guided Policy Optimization for Multi-Turn Agentic Tasks
Group-based reinforcement learning (RL) has become an effective paradigm for LLM post-training, but in multi-turn agentic tasks with sparse terminal rewards...
Accessing OpenAI models on Amazon Bedrock from Australia with global cross-Region inference
Australian teams can now access OpenAI GPT-5.6 Sol, Terra, and Luna models on Amazon Bedrock with global cross-Region inference from the Asia Pacific...