FUTURE WORK / INTERFACE

Conversation Flow tags

A proposed control vocabulary for MacroCF.

At each decision step, the interface would return one control tag, optionally preceded by a brief <think> block. The tags describe the next conversational decision; the application determines how that decision maps to playback, speech generation, or listening.

TagMeaningIntended interpretation
<EOT/>End of turnThe target speaker has finished a turn; a response may begin.
<INT/>InterruptionA participant is taking the floor; the application can yield or stop its own speech.
<LTN/>ListenContinue listening and waiting; there is not yet enough evidence to act.
<BC/>BackchannelA brief acknowledgement is appropriate while the other participant retains the floor.
<REJ/>Reject / no responseChoose not to respond to the current input, for example when the speech is not directed at the agent.

Listening and non-response are different

LTN means waiting for further context before deciding. REJ means deciding that the current input should not receive a response. Neither tag prevents reconsideration when new context arrives.

Optional <think> block

Reasoning-enabled example:

<think>The speaker is still developing the request; continue listening.</think>
<LTN/>

Direct-tag example:

<LTN/>

These are illustrative interface examples, not recorded model outputs. The <think> block is optional; one control tag remains required for each output step.

Decision cadence and actions

The design targets a decision every 200 ms using accumulated context. A repeated tag need not retrigger an application action: continuous listening can remain active across multiple steps, while discrete actions need application-level event handling.

Evaluation scope

The five-tag interface is a research direction for MacroCF. TurnBench EOT and INT event lists are a separate evaluation format. The existing MicroCF results do not measure LTN, BC, or REJ, nor do they validate this proposed interface.