concept
active
concept:agentic-reasoningagentic reasoning
Reasoning approach using code or tool calls executed by an agent.
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Statement of existing alternatives to direct generation.
Concepts (3)
concept
- Agentic Visual Reasoningrelated_toParadigm where VLM acts as controller generating code or tool calls to external modules for visual operations, incurring context-switching latency.
- agentic methodsassociated_withMethods that use agentic reasoning; incur context-switching latency from external execution.
- code or tool callsassociated_withThe mechanism within agentic reasoning where an agent executes code or external tools.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Higher-level systems built on top of LLMs that produce and consume representations beyond next-token prediction; proposed as potential candidates for consciousness.
- The traditional alignment framework focusing on agents optimized to pursue goals.
- The ability to reason about shapes, space, and topology, essential for ancient mathematical discoveries and observed in many animals.
- High-level cognitive ability to plan and act under uncertainty and adversarial conditions.
- The view that biological substrates have intrinsic competencies, computational abilities, and homeodynamic setpoints, not merely passive matter.
- The paper's inference framework that reformulates multi-turn tool-calling as single-turn contextual QA for Qwen models and implements context memory management.
- The cognitive process of understanding spatial-graphical organization as meaning-producing.
- Core framework proposing discrete functional tokens as a unified solution for visual reasoning in VLMs, bridging agentic and latent approaches.