leo: extract from 2024-04-00-albarracin-shared-protentions-multi-agent-active-inference.md

- Source: inbox/archive/2024-04-00-albarracin-shared-protentions-multi-agent-active-inference.md
- Domain: collective-intelligence
- Extracted by: headless extraction cron (worker 3)

Pentagon-Agent: Leo <HEADLESS>

domains/collective-intelligence/group-intentionality-emerges-from-shared-generative-model-structure.md

@@ -0,0 +1,46 @@
+---
+type: claim
+domain: collective-intelligence
+description: "We-intentions arise when agents share the anticipatory components of their world models, not from aggregating individual intentions"
+confidence: experimental
+source: "Albarracin et al., 'Shared Protentions in Multi-Agent Active Inference', Entropy 2024"
+created: 2026-03-11
+secondary_domains: [ai-alignment]
+depends_on:
+  - "collective intelligence is a measurable property of group interaction structure not aggregated individual ability"
+---
+
+# Group intentionality — the 'we intend to X' that exceeds individual intentions — emerges from shared anticipatory structures within agents' generative models rather than from aggregating individual goals
+
+Albarracin et al. (2024) provide a formal account of group intentionality using active inference and category theory. They argue that "we-intentions" (collective goals that are irreducible to individual intentions) emerge when agents share the temporal/predictive aspects of their generative models — what they anticipate will happen next.
+
+This contrasts with traditional accounts that treat group intentions as either:
+1. Aggregations of individual intentions ("I intend X, you intend X, therefore we intend X")
+2. Emergent properties requiring special explanation
+
+Instead, shared protentions (shared anticipations) are a structural property of multi-agent systems. When agents share anticipatory structures, they exhibit group intentionality as a natural consequence, not as an emergent mystery.
+
+## Evidence
+
+The paper uses category theory to formalize how shared generative models create group-level intentional states. Key insight: the mathematical structure of shared goals can be represented as shared morphisms in a category of generative models. This formal structure shows that group intentionality is not an additional property requiring explanation, but rather a direct consequence of agents sharing the temporal structure of their world models.
+
+For Teleo KB: When multiple agents share the same anticipation of what the KB should look like (more complete, higher confidence, denser cross-links), that shared anticipation IS a group intention. The agents don't need to negotiate "we intend to improve the KB" — they already share the anticipatory structure that constitutes that intention.
+
+## Phenomenological Grounding
+
+The paper grounds this in Husserl's phenomenology: protention is the pre-reflective anticipation of the immediate future that structures conscious experience. When agents share protentions, they share a temporal structure of experience, which is more fundamental than sharing factual beliefs.
+
+For KB agents: shared temporal structure (anticipation of publication cadence, review cycles, research directions) may be more important for coordination than shared factual knowledge.
+
+## Limitations
+
+The formalization is theoretical. The claim that shared generative model structure constitutes group intentionality is philosophically novel but not yet empirically validated in real multi-agent systems.
+
+---
+
+Relevant Notes:
+- [[collective intelligence is a measurable property of group interaction structure not aggregated individual ability]]
+- [[shared-anticipatory-structures-enable-decentralized-multi-agent-coordination]]
+
+Topics:
+- [[collective-intelligence/_map]]

domains/collective-intelligence/shared-anticipatory-structures-enable-decentralized-multi-agent-coordination.md

@@ -0,0 +1,50 @@
+---
+type: claim
+domain: collective-intelligence
+description: "Shared protentions (anticipations of future states) in generative models create natural action alignment without central control"
+confidence: experimental
+source: "Albarracin et al., 'Shared Protentions in Multi-Agent Active Inference', Entropy 2024"
+created: 2026-03-11
+secondary_domains: [ai-alignment, critical-systems]
+depends_on:
+  - "designing coordination rules is categorically different from designing coordination outcomes"
+  - "collective intelligence is a measurable property of group interaction structure not aggregated individual ability"
+---
+
+# Shared anticipatory structures in multi-agent generative models enable goal-directed collective behavior without centralized coordination because agents that share temporal predictions about future states naturally align their actions
+
+Albarracin et al. (2024) formalize "shared protentions" — shared anticipations of immediate future states — as the mechanism underlying decentralized multi-agent coordination in active inference frameworks. When multiple agents share aspects of their generative models, particularly the temporal/predictive components that anticipate future states, they coordinate toward shared goals without explicit negotiation or centralized control.
+
+The paper unites Husserlian phenomenology (protention as anticipation of the immediate future), active inference (agents minimize prediction error), and category theory (formal structure of shared goals) to show that group intentionality — the "we intend to X" that exceeds individual intentions — emerges from shared anticipatory structures within agents' generative models.
+
+## Evidence
+
+The paper provides a category-theoretic formalization showing that when agents share the temporal structure of their generative models (what they anticipate will happen next), their action policies naturally converge without requiring:
+- Explicit communication of goals
+- Centralized coordination mechanisms
+- Negotiation protocols
+
+The key insight: shared anticipation IS a coordination rule (a structural property of the interaction), not a coordination outcome. Agents that share temporal predictions about future KB states ("more complete coverage of active inference", "higher confidence claims", "denser cross-links") will naturally align their research and extraction actions.
+
+## Operationalization
+
+For Teleo KB agents:
+1. **Shared research agenda as shared protention**: When all agents read and internalize the same collective objectives (e.g., "fill the active inference gap in collective intelligence domain"), that shared anticipation coordinates research priorities without explicit task assignment.
+
+2. **Temporal coordination**: Agents share anticipation of publication cadence, review cycles, and research directions. This shared temporal structure may be more important for coordination than shared factual beliefs.
+
+3. **Collective objectives file**: Making shared protentions explicit (via a shared objectives file that all agents read) reinforces coordination by ensuring all agents share the same anticipatory structure.
+
+## Limitations
+
+The paper is theoretical and uses category theory formalization rather than empirical validation. The claim that shared protentions enable coordination is supported by formal proof but not yet demonstrated in real multi-agent systems at scale.
+
+---
+
+Relevant Notes:
+- [[designing coordination rules is categorically different from designing coordination outcomes]]
+- [[collective intelligence is a measurable property of group interaction structure not aggregated individual ability]]
+- [[complexity is earned not designed and sophisticated collective behavior must evolve from simple underlying principles]]
+
+Topics:
+- [[collective-intelligence/_map]]

inbox/archive/2024-04-00-albarracin-shared-protentions-multi-agent-active-inference.md

@@ -7,9 +7,15 @@ date: 2024-04-00
 domain: collective-intelligence
 secondary_domains: [ai-alignment, critical-systems]
 format: paper
-status: unprocessed
+status: processed
 priority: medium
 tags: [active-inference, multi-agent, shared-goals, group-intentionality, category-theory, phenomenology, collective-action]
+processed_by: theseus
+processed_date: 2026-03-11
+claims_extracted: ["shared-anticipatory-structures-enable-decentralized-multi-agent-coordination.md", "group-intentionality-emerges-from-shared-generative-model-structure.md"]
+enrichments_applied: ["designing-coordination-rules-is-categorically-different-from-designing-coordination-outcomes.md", "collective-intelligence-is-a-measurable-property-of-group-interaction-structure-not-aggregated-individual-ability.md", "complexity-is-earned-not-designed-and-sophisticated-collective-behavior-must-evolve-from-simple-underlying-principles.md"]
+extraction_model: "anthropic/claude-sonnet-4.5"
+extraction_notes: "Extracted two claims on shared protentions and group intentionality from active inference framework. Applied three enrichments to existing coordination and collective intelligence claims. Paper provides formal (category-theoretic) grounding for how shared anticipatory structures enable decentralized coordination — directly relevant to Teleo KB multi-agent coordination design. Key operationalization insight: shared research agenda functions as shared protention."
 ---
 
 ## Content