{"id":"7d4dd719-f261-4170-8fab-a25c94c41aa5","arxiv_id":"2604.03091","paper_version":1,"verdict":"UNVERDICTED","confidence":"LOW","novelty_score":5.0,"correctness_risk":"unknown","formal_verification":"none","parameter_count":0,"one_line_summary":"CASCADE is a cascading three-layer system for low-cost controllable NPC social coordination that uses macro events, modular decomposition, and tag-based execution to produce differentiated behaviors without per-agent LLM prompting in the main loop.","lead":"The paper presents CASCADE, a three-layer architecture that combines macro state tracking, a coordination hub for group directives, and tag-driven NPCs using behavior trees with selective LLM calls to enable scalable social simulation in games. Game developers and AI researchers may read it for a practical approach to balancing authorial control, behavioral richness, and runtime cost in large virtual worlds.","discovery_kind":"new_method","skeptic_critique":{"model":"grok-4.3","headline":"Trace-based micro-scenario evaluation leaves constraint preservation and per-agent cost claims untested at scale","rationale":"The reader's weakest assumption directly matches the load-bearing gap: reliable constraint preservation without extra per-agent work. The architecture description is internally consistent on paper, but the absence of any scaling experiment or automated constraint checker in the reported results means the claim remains conditional on larger validation. No formal verification or shipped code is present to offset this.","tokens_in":1676,"tokens_out":288,"duration_ms":19012,"concrete_test":"Take the largest micro-scenario from the paper, scale it to 100 NPCs with at least two overlapping tags, and run 20 sequential macro events; automatically verify that every behavior-tree leaf respects the logical constraints encoded in the domain components and that no LLM calls occur outside the documented on-demand player-facing path.","verdict_should_be":"CONDITIONAL","load_bearing_attack":"The central claim requires that macro-level causal updates routed through domain-specific components and tag-driven behavior trees produce differentiated NPC responses that stay logically constrained without per-agent prompting or LLM calls in the main loop. The evaluation section reports only micro-scenario prototypes and trace-based analysis; this does not examine directive conflicts across overlapping tags, state drift when on-demand LLM outputs feed back into the Macro State Director, or whether behavior-tree execution remains constraint-compliant once NPC count and event interleaving increase.","agreement_with_reader":"agree"},"referee_report":{"model":"grok-4.3","summary":"The manuscript introduces CASCADE, a three-layer cascading architecture for low-cost, controllable social coordination in sandbox-style game worlds. A Macro State Director (Level 1) maintains discrete-time world-state variables and performs macro-level causal updates. A modular Coordination Hub (Level 2) decomposes these updates through domain-specific components (e.g., professional and social coordination) and routes directives to tag-defined NPC groups. Tag-Driven NPCs (Level 3) execute responses via behavior trees and local state/utility functions, invoking LLMs only for on-demand player-facing interactions. Evaluation consists of micro-scenario prototypes and trace-based analysis demonstrating that a shared macro event can yield differentiated yet logically constrained NPC behaviors without per-agent prompting in the main simulation loop. The work positions CASCADE as a modular foundation for scalable social simulation and future open-world authoring tools.","tokens_in":1804,"tokens_out":725,"duration_ms":35821,"significance":"If the architecture reliably preserves logical constraints while generating differentiated behaviors at low per-agent cost, it would provide a practical bridge between rigid scripted NPC systems and high-cost fully LLM-driven agents, enabling more scalable and author-controllable social simulation in games. The modular decomposition via domain-specific components and tag-driven routing is a clear strength for extensibility and reduced runtime prompting. The conceptual design is sound and addresses a genuine tension in game AI, though the current lack of quantitative validation limits its immediate applicability.","major_comments":[{"comment":"Evaluation section: The central claim that macro-level causal updates routed through domain-specific components and tag-driven behavior trees produce differentiated, logically constrained NPC responses without per-agent prompting or LLM calls in the main loop is load-bearing, yet supported only by micro-scenario prototypes and trace-based analysis. No quantitative metrics (constraint violation rates, per-agent compute cost, scalability with increasing NPC count or event interleaving), error analysis, or tests for directive conflicts across overlapping tags or state drift from LLM feedback into the Macro State Director are reported. This leaves the weakest assumption untested at scale.","section":"Evaluation"},{"comment":"Coordination Hub description (Section 3.2): The mechanism for resolving potential conflicts when multiple domain-specific components issue directives to the same tag-defined group is not specified with pseudocode, decision rules, or examples. Without this, it is unclear how logical constraints are enforced when tag routing produces overlapping or contradictory directives.","section":"Section 3.2"}],"minor_comments":[{"comment":"The abstract states 'multiple micro-scenario prototypes' but the evaluation section does not enumerate the specific scenarios, their scale, or the exact traces analyzed, hindering reproducibility.","section":"Abstract and Evaluation"},{"comment":"Behavior-tree execution and local utility functions in Level 3 are referenced but lack even high-level pseudocode or a diagram showing how tag inputs map to tree nodes and utility calculations.","section":"Section 3.3"},{"comment":"A brief related-work subsection contrasting CASCADE explicitly with existing hybrid NPC systems (e.g., those using behavior trees with occasional LLM calls) would clarify the novelty of the cascading macro-to-tag routing.","section":"Introduction"}],"recommendation":"major_revision","confidential_remarks":"This manuscript is primarily an architecture/systems description with prototype traces rather than a rigorous empirical study. It may align better with a systems or game-AI venue than a core HCI or AI journal that expects quantitative evaluation of claims."},"author_rebuttal":{"model":"grok-4.3","summary":"We thank the referee for the constructive review and for recognizing the potential of the CASCADE architecture. We address each major comment below and indicate planned revisions to strengthen the manuscript.","responses":[{"response":"We agree that the evaluation relies on micro-scenario prototypes and trace-based analysis to illustrate differentiated, constrained behaviors at low cost, without large-scale quantitative validation. This limitation is acknowledged. In the revised manuscript we will expand the evaluation to report quantitative metrics including constraint violation rates, per-agent compute cost, and scalability under increasing NPC counts and interleaved events, along with error analysis for directive conflicts and state drift.","revision_made":"yes","referee_comment":"[Evaluation] Evaluation section: The central claim that macro-level causal updates routed through domain-specific components and tag-driven behavior trees produce differentiated, logically constrained NPC responses without per-agent prompting or LLM calls in the main loop is load-bearing, yet supported only by micro-scenario prototypes and trace-based analysis. No quantitative metrics (constraint violation rates, per-agent compute cost, scalability with increasing NPC count or event interleaving), error analysis, or tests for directive conflicts across overlapping tags or state drift from LLM feedback into the Macro State Director are reported. This leaves the weakest assumption untested at scale."},{"response":"The manuscript describes the Coordination Hub at the architectural level but does not supply explicit pseudocode, decision rules, or worked examples for conflict resolution. We accept this as a gap that reduces clarity on constraint enforcement. Section 3.2 will be revised to include a precise specification of the resolution mechanism (domain-priority ordering with tie-breaking by recency), accompanied by pseudocode and concrete examples of overlapping directives.","revision_made":"yes","referee_comment":"[Section 3.2] Coordination Hub description (Section 3.2): The mechanism for resolving potential conflicts when multiple domain-specific components issue directives to the same tag-defined group is not specified with pseudocode, decision rules, or examples. Without this, it is unclear how logical constraints are enforced when tag routing produces overlapping or contradictory directives."}],"tokens_in":1479,"tokens_out":448,"duration_ms":26401,"standing_objections":[]},"desk_editor":{"model":"grok-4.3","letter":"The main point is that this paper describes a practical split: a Macro State Director handles discrete world updates, a Coordination Hub decomposes those into domain-specific directives and routes them by tags, and Tag-Driven NPCs run local behavior trees with LLM calls only when a player directly interacts. That selective pattern is the actual new piece. It lets one macro event produce varied NPC responses without prompting every agent in the main loop, which is a sensible middle path between rigid scripts and full per-agent models. The modular hub and tag routing are described clearly enough that someone could implement the skeleton from the text.","headline":"CASCADE gives a clean three-layer hybrid for controllable low-cost NPC social behavior in games, but the micro-scenario traces do not test the scalability or constraint claims at any meaningful size.","tokens_in":2264,"tokens_out":200,"would_cite":false,"duration_ms":41609,"reading_group":"maybe","serious_thinker":"yes","would_accept_peer_review":true},"rs_alignment":{"model":"grok-4.3","evidence":[{"relation":"unclear","rs_module":"IndisputableMonolith/Foundation/ArithmeticFromLogic.lean","rs_theorem":"reality_from_one_distinction","paper_passage":"CASCADE is a three-layer architecture... Macro State Director... Coordination Hub... Tag-Driven NPCs execute responses through behavior trees and local state/utility functions"}],"headline":"Cascading macro-meso-micro coordination for NPC behavior trees is orthogonal to RS distinction-to-physics forcing","alignment":"orthogonal","rationale":"The paper's central machinery (Macro State Director + Coordination Hub + tag-driven behavior trees with local utility calculus) is a practical engineering decomposition for low-cost game simulation. It contains no recognition-cost function J, no golden-ratio ladder, no 8-tick periodicity, and no derivation of constants from a single distinction. RS modules on social simulation (e.g., Sociology, GameTheory) derive J-shaped structural theorems; this work does not invoke or parallel any of them.","tokens_in":43530,"confidence":"high","tokens_out":230,"duration_ms":17520,"cache_read_input_tokens":128,"cache_creation_input_tokens":0},"lean_confirmation":null,"pith_extraction":{"msc":[],"pacs":[],"model":"grok-4.3","headline":"CASCADE uses macro states, a coordination hub, and tag-driven NPCs to produce varied social behaviors at low cost without per-agent LLM calls in the loop.","keywords":["social simulation","NPC behavior","game AI architecture","controllable emergence","scalable coordination","behavior trees","LLM agents"],"falsifier":"A prototype run in which a single macro event produces identical or contradictory actions from NPCs that carry different tags would show the routing mechanism fails to deliver constrained differentiation.","tokens_in":2579,"feed_emoji":"🎮","tokens_out":608,"duration_ms":36104,"temperature":0.7,"pith_summary":"CASCADE proposes a three-layer architecture for social simulation in sandbox games. The top Macro State Director tracks discrete world variables and applies causal updates at each time step. A modular Coordination Hub then decomposes those updates through domain-specific components and routes directives to groups of NPCs identified by tags. The NPCs respond locally with behavior trees and utility functions, calling language models only for player-facing moments. This structure keeps the main simulation loop cheap while still letting shared events generate differentiated yet logically bounded NPC actions.","feed_headline":"Macro states and tags let NPCs react differently without per-agent LLM calls","feed_subtitle":"CASCADE's three layers keep social simulation costs low while producing differentiated yet constrained group behaviors","key_machinery":"The three-layer cascading architecture: Macro State Director for world-state maintenance, Coordination Hub with domain-specific decomposition and tag routing, and Tag-Driven NPCs executing via behavior trees and local state functions.","core_discovery":"The central claim is that separating macro-level causal updates from per-NPC execution, routing changes through domain-specific components in a Coordination Hub, and triggering responses via tags allows shared events to produce differentiated NPC behaviors that remain logically constrained without invoking LLMs for every agent on every tick.","pith_inferences":["The design could support open-world games with thousands of NPCs where full per-agent LLM simulation would exceed practical compute limits.","Trace analysis of macro-to-NPC propagation might become a standard debugging tool for large social simulations.","Designers could eventually author new domain components as plug-ins to expand coordination rules without touching core NPC code."],"forward_implications":["A single macro event can trigger varied NPC reactions based on their tags and local utilities while preserving global constraints.","LLM usage stays limited to on-demand player interactions, keeping runtime cost low even with many agents.","New coordination domains can be added by extending the Coordination Hub without rewriting NPC behavior logic.","Authors gain control through macro updates and tag groups rather than scripting every individual response."],"fun_headline_variants":["Macro states and tags differentiate NPC reactions without per-agent calls","CASCADE cascades macro updates through tags for varied NPC behaviors","Tags enable differentiated yet constrained NPC responses from macro events","Three-layer CASCADE delivers low-cost controllable social NPC simulation"],"cache_read_input_tokens":64,"weakest_assumption_plain":"Macro causal updates and tag-based routing can reliably generate believable, differentiated NPC responses that stay logically consistent across scenarios without extra per-agent computation or LLM calls.","fun_headline_variants_meta":{"raw":{"variants":["Macro states and tags differentiate NPC reactions without per-agent calls","CASCADE cascades macro updates through tags for varied NPC behaviors","Tags enable differentiated yet constrained NPC responses from macro events","Three-layer CASCADE delivers low-cost controllable social NPC simulation"]},"model":"grok-4.3","cost_usd":0.00739,"raw_usage":{"total_tokens":3287,"prompt_tokens":608,"num_sources_used":0,"completion_tokens":63,"cost_in_usd_ticks":73903000,"prompt_tokens_details":{"text_tokens":608,"audio_tokens":0,"image_tokens":0,"cached_tokens":64},"completion_tokens_details":{"audio_tokens":0,"reasoning_tokens":2616,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"tokens_in":608,"tokens_out":63,"duration_ms":32151,"temperature":1.0,"reasoning_tokens":2616,"cache_read_input_tokens":64,"cache_creation_input_tokens":0},"cache_creation_input_tokens":0},"created_at":"2026-05-13T18:20:48.398924+00:00","model_set":{"reader":"grok-4.3"},"falsifier":"A prototype run in which a single macro event produces identical or contradictory actions from NPCs that carry different tags would show the routing mechanism fails to deliver constrained differentiation.","supporting_citations":[],"review_version":1}