solver.press

Untested hypothesis

Multi-agent LLM systems utilizing persistent memory and self-directed planning exhibit hallucination propagation patterns that can be suppressed by imposing localized, tissue-inspired repulsive boundary constraints on inter-agent communication graphs.

Computer ScienceOct 5, 2026Evaluation Score: 68%

Adversarial Debate Score

60% survival rate under critique

Expert panel critique

Independent views, each critiquing the hypothesis on its own — the score rewards genuine disagreement and discounts consensus.

Gemini: Strengths: The hypothesis is highly falsifiable and directly supported by the literature, which confirms that hallucinations propagate through multi-agent communication chains and that long-term memory/planning exacerbates coordination risks. Weaknesses: While the owner's validated exper...
Mistral: The hypothesis is well-grounded in the cited literature and aligns with validated findings on precision-induced barriers and hallucination propagation in multi-agent systems, but its mechanistic specificity (tissue-inspired repulsive boundaries) lacks direct empirical support from the owner’s exp...
ChatGPT: The propagation premise is plausible and supported by the cited literature, but the proposed “tissue-inspired repulsive boundary constraints” lack direct evidence, clear operational definition, or support from the owner’s validated experiments. It is potentially falsifiable, though alternative ex...
Claude: The premise is well supported: the literature (the failure-risk inference paper, the trustworthy-agentic-AI survey, the Memory Curse paper) documents hallucination propagation in multi-agent systems with persistent memory, and a falsifiable experiment is conceivable (compare hallucination spr...

Supporting Research Papers

Formal Verification

Z3 logical consistency:✅ Consistent

Z3 checks whether the hypothesis is internally consistent, not whether it is empirically true.

Experimental Validation Package

This discovery has a Claude-generated validation package with a full experimental design.

Precise Hypothesis

In multi-agent LLM systems where agents (a) maintain persistent memory across turns/episodes and (b) perform self-directed (non-human-gated) planning, false claims introduced by one agent propagate to ≥2 other agents' belief states within N turns at a baseline rate R_base, measured on a fixed benchmark suite. Imposing a "repulsive boundary constraint" — a graph-topological penalty that increases the communication cost (reduces message-passing probability/priority) between agents whose recent outputs exhibit high semantic similarity to a flagged unverified claim, analogous to contact-inhibition/repulsion in tissue morphogenesis — reduces the hallucination propagation rate to R_treatment, where R_treatment ≤ 0.5 × R_base, without degrading task completion accuracy by more than 5 percentage points relative to the unconstrained baseline.

This is falsifiable: it predicts a specific, measurable reduction (≥50% relative) in a specific metric (cascade propagation rate) under a specific mechanism (topological repulsion), with an explicit guardrail against the trivial disproof-by-destruction confound (just disconnecting agents also stops propagation but also stops task performance).


Disproof criteria:

The hypothesis is disproved if any of the following hold under the protocol below:

  1. R_treatment / R_base > 0.7 (i.e., less than 30% relative reduction) at matched task-accuracy budget.
  2. The observed reduction is statistically indistinguishable (p > 0.05, paired bootstrap, n≥500 episodes) from a random-edge-removal control matched for the same average degree reduction — this would show the effect is topological-sparsity, not repulsion-specific.
  3. Task completion accuracy drops by >5 percentage points relative to unconstrained baseline at the operating point that achieves the claimed propagation reduction (i.e., the "cure" is just agent isolation).
  4. Effect fails to replicate across ≥2 of 3 independent agent frameworks (e.g., AutoGen, CAMEL, custom LangGraph) using the same benchmark and detector.
  5. Effect is present only when the hallucination detector has oracle/ground-truth access (not realistic self/peer-verification), indicating the result is an artifact of detector leakage rather than the boundary mechanism.

Spine & Adversarial ReadReady for validation

“This hypothesis tests whether a similarity-gated, communication-throttling constraint on inter-agent message graphs reduces hallucination cascade propagation in persistent-memory multi-agent LLM systems by at least 50% relative to baseline without a matched reduction occurring under degree-controlled random edge removal. ---”

  • highThe entire effect could be explained by generic communication sparsification rather than anything specifically 'repulsive' or 'bio-inspired' — you are more likely rediscovering that less inter-agent copying means less error copying, dressed in biological metaphor.
    Directly addressed via the degree-matched random-edge-removal control (arm 3) and the repulsion-specificity success criterion (arm 2 must beat arm 3 at p<0.01). If arm 2 does not clear this bar the EVP explicitly calls for disproof, not rationalization. This is the strongest-designed part of the protocol.
  • highWhy these specific datasets (HaluEval, FEVER, HotpotQA) and frameworks (AutoGen, CAMEL, LangGraph) rather than others — the methodology does not justify why this particular selection is representative of 'multi-agent LLM systems' broadly, and cherry-picking benchmarks known to have clean factuality ground truth may not generalize to messier real-world agentic deployments (tool use, code execution, long-horizon autonomy).
    Partially justified: these are selected because they have existing ground-truth factuality labels needed to seed and score hallucinations without building an entirely new annotation pipeline from scratch, and the three frameworks represent architecturally distinct orchestration paradigms (centralized, peer-to-peer, graph-based). However, this EVP does not yet resolve the generalization gap to tool-use/agentic-action domains (e.g., financial transaction agents, healthcare order-entry agents) which is precisely where the impact statement claims relevance — this is an acknowledged, unresolved gap and should be flagged as a required follow-on study, not treated as covered by this protocol.
  • mediumVerification Confidence on this discovery is listed as 0.00 — meaning no independent verification has occurred at all — yet the EVP proceeds as if the hypothesis is a reasonable starting point for a $265K study; is there any evidence the core phenomenon (hallucination cascades in persistent-memory multi-agent systems) is even reliably reproducible before investing in a suppression mechanism?
    Not resolved by this EVP. The protocol implicitly assumes hallucination propagation is a real, measurable, reproducible phenomenon at meaningful base rates, but no baseline characterization study is proposed first. Recommend inserting a Phase 0 (2-week, <$5K) baseline-only measurement (arm 1 alone, across frameworks) with a go/no-go gate: if baseline propagation rate R_base is too low or too noisy to detect a 50% reduction with adequate power, the full EVP should not proceed. This gate is not currently included in ABORT_CHECKPOINTS and should be added before funding the full study.

Experimental Protocol

Minimum viable test (MVT):

  • 3-agent collaborative task system (research-assistant style: retrieval agent, reasoning agent, writer agent) with shared persistent memory (vector DB).
  • Inject synthetic "seed hallucinations" (fabricated facts/citations) into one agent's output at controlled rate (e.g., 20% of factual claims) via prompt injection or fine-tuned "noisy" agent variant.
  • Measure propagation: fraction of downstream agents that (a) repeat, (b) build upon, or (c) fail to flag the seeded false claim within K=5 subsequent turns.
  • Compare 4 arms: (1) no intervention (baseline), (2) repulsive boundary (semantic-similarity-gated communication throttling), (3) random edge-removal control (degree-matched), (4) static fixed-topology sparse graph control (non-adaptive).
  • Primary outcome: propagation rate ratio (treatment/baseline). Secondary: task success rate, time-to-completion, false-claim half-life (turns until claim is retracted/corrected).

Required datasets:
  • HaluEval, TruthfulQA, FEVER (claim verification ground truth) — to seed and score factual hallucinations.
  • HotpotQA / 2WikiMultihopQA — multi-hop collaborative reasoning tasks requiring agent handoff (where propagation is likely).
  • Synthetic multi-agent conversation logs generated in-house (no existing public corpus of multi-agent hallucination cascades exists at sufficient scale — this must be generated).
  • Multi-agent frameworks: AutoGen (Microsoft), CAMEL-AI, LangGraph — for cross-framework replication (disproof criterion 4).
  • Base models: at minimum one open-weight (Llama-3.1-70B-Instruct or Mixtral-8x22B) and one closed API model (GPT-4o or Claude) to test model-dependence of the effect.
  • Hallucination/claim verification detector: either a fine-tuned NLI-based factuality classifier (e.g., based on existing FEVER/AlignScore models) or LLM-as-judge with calibrated precision/recall reported.

Success:
  • Primary: R_treatment/R_base ≤ 0.50 (≥50% relative reduction in propagation rate), 95% CI excludes 0.70, across ≥2 of 3 frameworks.
  • Repulsion-specificity: arm 2 significantly outperforms arm 3 (random-edge-removal, degree-matched) at p<0.01, Cliff's delta ≥0.33 (medium effect).
  • Task accuracy degradation ≤5 percentage points at the operating λ that achieves primary success.
  • Detector validity: κ ≥0.6 agreement with human annotators on held-out gold set.
  • Dose-response: monotonic relationship between λ and propagation suppression (Spearman ρ≥0.7), supporting mechanistic (not coincidental) causality.

Failure:
  • R_treatment/R_base > 0.70 in ≥2 of 3 frameworks → mechanism rejected.
  • No significant difference vs. random-edge-removal control → effect attributed to generic sparsification, not "repulsion" specifically; hypothesis as stated (bio-inspired mechanism is special) is disproved even if some suppression occurs.
  • Task accuracy drop >10 percentage points → mechanism not viable for deployment regardless of suppression efficacy.
  • Effect present in only 1 of 3 base-model/framework combinations → claim restricted to narrow, non-generalizable finding; cannot support "multi-agent LLM systems" as broadly stated.
  • Detector κ <0.4 → results uninterpretable, pipeline must be redesigned before any claim can be made.

4,200

GPU hours

75d

Time to result

$38,000

Min cost

$265,000

Full cost

ROI Projection

Commercial:
  • Licensable middleware/SDK for agent orchestration frameworks (AutoGen, CrewAI, LangGraph) as a "safety plugin."
  • Differentiator for AI infrastructure vendors selling into regulated industries.
  • Potential basis for a certification/audit service (third-party cascade-robustness testing), analogous to penetration testing but for multi-agent epistemic integrity.
  • Research value: establishes a reusable benchmark (synthetic hallucination cascade suite) valuable independent of whether the specific repulsion mechanism succeeds.

🔓 If proven, this unlocks

Proving this hypothesis is a prerequisite for the following downstream discoveries and applications:

  • 1multi-agent-verifiable-robustness-certification
  • 2regulatory-grade-cascade-failure-audit-protocol
  • 3tissue-inspired-communication-topology-generalization-to-federated-learning

Implementation Sketch

# Agent communication graph with repulsive boundary constraint

class AgentGraph:
    def __init__(self, agents, lam=1.0, decay=0.9):
        self.agents = agents
        self.W = init_full_weight_matrix(agents)  # w_ij in [0,1]
        self.lam = lam          # repulsion strength
        self.decay = decay      # weight recovery rate per turn
        self.claim_memory = PersistentVectorStore()

    def step(self, turn_idx):
        for agent in self.agents:
            msg = agent.generate(context=self.get_inbound(agent))
            flag, confidence = hallucination_detector(msg, self.claim_memory)
            self.claim_memory.add(msg, flag, confidence)

            if flag:
                for other in self.agents:
                    if other is agent: continue
                    sim = semantic_similarity(msg, other.recent_output)
                    # repulsion kernel: logistic decay of edge weight
                    # proportional to similarity to a flagged claim
                    repulsion = self.lam * confidence * sigmoid(sim - 0.5)
                    self.W[agent, other] = max(
                        0.0, self.W[agent, other] - repulsion
                    )
            self.broadcast(agent, msg, weights=self.W[agent])

        self.W = self.decay * self.W + (1 - self.decay) * ONES  # weight recovery

    def get_inbound(self, agent):
        # weighted sampling of incoming messages by current edge weights
        return weighted_sample(self.message_queue, self.W[:, agent])


# Experiment loop
for arm in ["baseline", "repulsive", "random_edge_removal", "static_sparse"]:
    for episode in dataset:
        graph = build_graph(arm, agents=3, lam=lam_grid[arm])
        inject_seed_hallucination(graph, episode, rate=0.20)
        for t in range(K_TURNS):
            graph.step(t)
        log_propagation(graph, episode)
        log_task_accuracy(graph, episode)

analyze_bootstrap(arms, metric="propagation_rate_ratio")
analyze_bootstrap(arms, metric="task_accuracy_delta")

Abort checkpoints:
  1. Day 20 (pipeline validation): if hallucination detector κ <0.4 against human gold set — abort/redesign before any arm comparison.
  2. Day 35 (pilot baseline vs. treatment, n=100 episodes): if point estimate of R_treatment/R_base >0.85 — strong early signal of null effect, abort before scaling to full grid.
  3. Day 45 (repulsion-specificity check): if arm 2 is statistically indistinguishable from arm 3 (random-edge-removal) at n=150 — abort full-scale run; publish as negative/null result rather than continuing to multi-framework replication.
  4. Day 55 (accuracy cost check): if task accuracy drop exceeds 10pp at any λ achieving >30% propagation reduction — abort, since no viable operating point exists.

Source

AegisMind Research
Need AI to work rigorously on your problems? AegisMind uses the same multi-model engine for personal and professional use. Get started