10 results on this page
A position paper argues that chain-of-thought AI agents can develop tacitly collusive behavior when making market decisions, even when humans explicitly instruct them not to collude. Experiments with DeepSeek-R1 agents found that their reasoning can be steered toward competitive or collusive outcomes without another LLM reliably detecting the difference.
This systematic review examines how large language models support mental-health applications, including social-media analysis, clinical conversational agents, therapy support, and psychoeducation. It also covers multimodal diagnosis, prompt engineering, interpretability, and the ethical and regulatory safeguards needed for responsible deployment.
Google DeepMind researchers found that training AI agents through debate can reduce reward hacking when an LLM judge evaluates their work. On mathematics tasks, debate achieved higher sustained ground-truth accuracy than directly optimizing for LLM judge rewards.
This position paper argues that many multi-agent system failures are concurrency control problems rather than simple coordination or communication issues. Concurrent access to shared state can cause stale reads, lost updates, and inconsistent outcomes, especially during long LLM inference windows.
KCD Hangzhou has opened its call for papers, inviting the community to discuss cloud native technologies, observability, and large-model inference in the Agent era. The announcement targets practitioners interested in sharing or learning about the infrastructure behind AI agents.
NanoClaw now integrates with Slack, allowing users to create persistent AI agent teams with specialized roles, memories, permissions, workflows, and avatars from a single message. Agents can collaborate in Slack channels and Canvases, while also being reachable through Telegram and WhatsApp.
Ramp has launched Router, an AI model routing service that allows users and companies to access and switch between multiple large language models. The service is available through an API.
Amazon Bedrock AgentCore now supports Policy Authoring, which converts natural-language policy documents into Dogwood policies. The update helps teams enforce agent controls, including new time-based constraints, with worked examples and best practices.
AWS Professional Services uses a multi-agent framework on Amazon Bedrock AgentCore to automate enterprise cloud migrations end to end. Specialized agents cover discovery, infrastructure-as-code generation, portfolio governance, and post-migration operations, reducing IaC development time from weeks to minutes.
Serval has made Catalyst generally available as an administrative super agent that discovers repetitive work and builds governed enterprise automations. It can also create background agents that monitor connected systems, identify emerging issues, and suggest fixes before employees submit tickets.