Theme of inquiry
How does AI reshape human skill, access, and competitive advantage?
A question within its area, explored through 6 lines of inquiry below — each a family of specific questions the research asks.
51 specific questions
- Can individual skills improve through reuse and accumulate experience across tasks?
- Can agentic reasoning outperform rigid rule-based systems for skill refinement?
- Can agent-authored skill libraries compound autonomy gains over time?
- Do learned workflows transfer between different agents with minimal accuracy loss?
- Can skill repositories evolve toward execution-oriented refinement over time?
- Can agent skills move from prompts to trainable parameters?
- Why do AI agents struggle with novel experiments but excel at routine tasks?
16 specific questions
- Does internal task decomposition eliminate overhead from multi-agent coordination?
- At what task difficulty does multi-agent decomposition become worth the coordination cost?
- When does multi-agent scaling actually outperform static ensembles?
- Which research tasks are better suited for multi-agent versus single-agent approaches?
- Does parallel task structure determine optimal multi-agent architecture?
- Can multi-agent teams solve problems better than single models thinking longer?
- How do static team decomposition and dynamic agent selection compare in efficiency?
7 specific questions
- How do planning and grounding have opposing optimization requirements in agents?
- Why do planning and grounding have opposing optimization requirements in agents?
- How should agents separate planning from perception grounding?
- Does the planning-grounding factoring principle apply to other agent tasks?
- What interference occurs when planning and synthesis happen in the same component?
- What does an intermediate interface between planning and grounding actually look like?
- What are the five inseparable design choices when building world models?
57 specific questions
- Do agents inform neighbors when adopting strategies in their reasoning?
- How do multi-agent systems improve on single frontier models?
- Can cognitive diversity compensate for lack of expertise in agent teams?
- Can cooperative AI systems make meaningful decisions without a stable self?
- Do explicit reward structures enable AI agent cooperation that open-ended interaction cannot?
- Can agents develop shared abstractions through communication pressure alone?
- Does genuine cooperation require rule-based rather than learned behavior?
31 specific questions
- What coordination failures emerge when multiple agents work together?
- How do multi-agent LLM systems fail at coordination and role consistency?
- Do multi-agent language model teams fail the same way individual reasoning does?
- How does silent agreement differ from failure to converge in multi-agent systems?
- What distinguishes task failure from communication breakdown in multi-agent systems?
- Which failure mode most limits current multi-agent performance?
- Can multi-agent LLM systems overcome diversity collapse through structured disagreement?
17 specific questions
- What makes evolving the benchmark different from evolving the optimizer itself?
- Can the same problem be solved by multiple evolutionary search strategies?
- Can moving or evolving objectives prevent misalignment in discovery agents?
- How do evolutionary archives enable diverse exploration in self-improving systems?
- How does compiling natural language goals into executable code enable objective evolution?
- Can evolutionary approaches avoid the overthinking failure mode of iterative refinement?
- Can objective search escape the limitations of fixed-objective central planning?