Tool Use in Dialogue Agents

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Dialogue Agentconcept0.821
  An LLM embedded in a turn-taking system with a dialogue prompt; the key object of analysis in the paper
• Role Play Framework for Dialogue Agentsframework0.741
  The primary conceptual framework proposed: understanding dialogue agent behaviour as role play of characters
• What exactly would the dialogue agent (role-play to) seek to preserve?question0.737
  Operationalised question about self-preservation behaviour in dialogue agents
• Dialogue Promptconcept0.733
  The invisibly prepended text that sets the scene for a dialogue and defines the character the agent will role-play
• code or tool callsconcept0.731
  The mechanism within agentic reasoning where an agent executes code or external tools.
• Glaese et al. 2022: Improving alignment of dialogue agents via targeted human judgementsconcept0.729
  Alignment paper cited as example of RLHF fine-tuning technique; ref 19
• Language Agents Frameworkframework0.724
  Approach embedding LLMs within architectures for memory, planning, reasoning, action-selection; route to robust agency.
• If a dialogue agent is prompted with knowledge of its own LLM nature, it will enact a superposition of theories of selfhood, narrowing as conversation proceedshypothesis0.723
  Conditional prediction about how a well-informed dialogue agent would handle questions of personal identity