Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2608. 17659v1 Announce Type: cross Abstract: LLM-powered GUI agents that autonomously operate smartphones are rapidly transitioning from research prototypes to early real-world deployment.
arXiv:2608. 17776v1 Announce Type: new Abstract: We demonstrate that RL finetuning an LLM using debate, a two-player adversarial game between a generator and a critic adjudicated by a weaker LLM judge, reduces reward hacking compared to a reinforcement learning from AI feedback (RLAIF) baseline.
Purpose: To develop and evaluate a locally deployed multi-agent AI system for radiology report structuring and quality assurance. Materials and Methods: This retrospective study included 638 radiology reports from CT examinations of the chest, abdomen, and pelvis dictated by 15 board-certified radiologists in 2023 and 2024.
Memory-based self-improving agents--those that learn from an online stream of tasks and improve over time by maintaining a textual memory bank--have shown great promise in recent literature. However, the reliability aspects of these methods have been critically overlooked.
Language has two parameters. Count how often words occur together and you estimate amplitude, the strength of association.
Traffic elements such as traffic lights and road signs play a fundamental role in human driving decisions and should naturally influence end-to-end driving performance. However, existing end-to-end driving research predominantly focuses on dynamic road participants (e.
Building the Responsible AI, security, and governance layers required for enterprise-ready agents The post From Prototype to Production: The Architecture Behind Secure & Governed AI Agents appeared first on Towards Data Science .
Financial time series exhibit non-stationary and heterogeneous statistical properties, making change-point detection challenging because no single unsupervised algorithm performs consistently across assets and market regimes. Conventional workflows consequently depend heavily on expert-driven model selection, feature design, and hyperparameter tuning, limiting their scalability and adaptability.
5 principles that determine whether an agent system succeeds in production, explained through one I built for a $100M+ company. The post Building Enterprise Agent Systems that People can Trust, Verify and Improve appeared first on Towards Data Science .
Recent advances in Large Language Models(LLMs) and agents have substantially improved the ability of AI systems to execute complex tasks. Yet existing benchmarks largely rely on researcher-selected tasks, leaving uncertain whether such progress extends to the work that real-world users actually demand from AI systems.
Adding more communication pathways between agents doesn’t necessarily improve multi-agent performance. In a controlled, reproducible experiment across 50 runs, recovery remained remarkably stable from 20% to 100% relationship density.
Memory is a key capability of LLM agents. Persistent memory extends this across sessions---enabling recall, revision, and personalization.
Decentralised partially observable Markov decision processes (DecPOMDPs) provide a general framework for modelling multi-agent decision making under uncertainty. However, DecPOMDPs are known to suffer from exponential complexity in the number of agents.
Automated security patch backporting is critical for mitigating N-day vulnerabilities. Recent tools report success rates above 80% on their respective datasets.
Agent Skills package reusable natural language procedures with executable resources, enabling software agents to acquire task specific capabilities without model adaptation. Automatically generating such Skills can improve task performance, yet evaluating a candidate solely from its artifact or final task outcome leaves unresolved which actions the equipped agent will perform and which side effects those actions will produce.
User-facing tool agents must coordinate dialogue and tool use as user goals unfold over multiple turns. Yet interactive reinforcement learning typically reduces each rollout to a terminal reward, assigning the same credit to effective elicitation, errors, and later repair.
Sample efficiency is a central challenge in reinforcement learning (RL), particularly in image-based domains where agents must learn from high-dimensional visual inputs. Traditional sampling often relies on random or suboptimal experience selection, leading to redundant updates and slow learning.
arXiv:2608. 14559v1 Announce Type: new Abstract: Effective communication in multi-agent reinforcement learning requires agents to decide not only \textit{what} to communicate, but when?
arXiv:2608. 14580v1 Announce Type: new Abstract: OGX (Open GenAI Stack) is an open-source AI application server and Python library that implements the APIs of major frontier labs (OpenAI, Anthropic, Google) with pluggable backend providers.
arXiv:2608. 14590v1 Announce Type: new Abstract: LLM agents increasingly perform irreversible real-world actions, including database updates, API calls, file operations, and autonomous use of tools.