concept
active
concept:agentic-visual-reasoningAgentic Visual Reasoning
Paradigm where VLM acts as controller generating code or tool calls to external modules for visual operations, incurring context-switching latency.
Neighborhood — ranked by edge-count
Frameworks (1)
framework
- ATLAS: Agentic or Latent Visual Reasoningassociated_withCore framework proposing discrete functional tokens as a unified solution for visual reasoning in VLMs, bridging agentic and latent approaches.
Concepts (1)
concept
- agentic reasoningrelated_toReasoning approach using code or tool calls executed by an agent.
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.
- Visual reasoning tasks often interleaved with intermediate visual states; promising direction in the field.
- The ability to reason about shapes, space, and topology, essential for ancient mathematical discoveries and observed in many animals.
- The paper's thesis from the title.
- Higher-level systems built on top of LLMs that produce and consume representations beyond next-token prediction; proposed as potential candidates for consciousness.
- The cognitive process of understanding spatial-graphical organization as meaning-producing.
- The traditional alignment framework focusing on agents optimized to pursue goals.
- Methods that use agentic reasoning; incur context-switching latency from external execution.
- Author's interpretive assertion on the direction of the field.