Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
MATM removes the repeated rediscovery cost baked into stateless agent deployments by giving heterogeneous agent populations a shared, retrievable store of procedural experience — without requiring joint training or inter-agent coordination.
Redteam introduces a human-gated, dual-model review structure that directly counters the single-model blind spot of an AI both writing and approving its own code.
Agent Canvas moving to production readiness marks a shift from experimental to officially supported tooling for running parallel AI agents and automations within the OpenHands ecosystem.
The talk reframes enterprise AI deployment failures as systemic infrastructure gaps — not model selection problems — showing that observability, evaluation pipelines, and governance tooling must be built before a model is even chosen.
The RATs framework demonstrates that self-directed play — without any explicit task instructions — can build a reusable, transferable code skill library that improves both in-distribution and real-world robot task performance without retraining the underlying model.
The decomposition replaces impractical logprob- and training-based uncertainty methods with a prompt-only approach that works under real deployment constraints, enabling LLM agents to proactively seek clarification on ambiguous tasks rather than acting on underspecified instructions.
The template removes the manual work of replicating a complex 64-agent, 261-skill Claude Code configuration by packaging it as a one-click, fully isolated microVM fork with the creator's persisted state included.
NRT-Bench reveals that frontier LLM agents are vulnerable to adaptive multi-turn attacks even in safety-critical supervisory roles, and that model-specific, nearly non-overlapping failure modes mean aggregate robustness metrics can mask significant individual weaknesses.
The structured shared history design directly resolves the tradeoff between inter-module context blindness and context rot, recovering cache prefix consistency while keeping per-module token consumption bounded in enterprise agentic systems.
The paper provides a measurable, formal account of how evaluation bias spreads in multi-agent LLM pipelines and identifies a concrete structural intervention — expanding evaluator committee size — that reduces that spread by 72.4%.