Rare, Relevant, and Still Wrong: How Memory Fails LLM Group Decisions

Anouar Imel, Imad Charradi, Abderrahman Sghir, Khalil El KhammararXiv 2026 · arXiv

When a group of AI agents discusses a complex problem, the resulting transcript can be massive. To make a final decision, we often compress that discussion into a "memory" or summary. But what should that memory prioritize?

A new paper, "Rare, Relevant, and Still Wrong: How Memory Fails LLM Group Decisions," reveals that our go-to strategies for summarizing AI group talk are surprisingly fragile. By introducing a new diagnostic benchmark called CrossProfile, the researchers demonstrate that LLMs are prone to "social proof" biases and that the most common ways we filter information can actually lead models toward the wrong answer.

TL;DR

Compression heuristics like prioritizing "rare" or "relevant" facts often fail in multi-agent decision-making because they don't account for the balance of evidence. The authors find that LLMs suffer from a "social proof" bias—overweighting facts mentioned by multiple agents—and that the biggest failure often happens "upstream" during the discussion itself, before memory is even created.

What Problem Does This Paper Address?

The authors focus on hidden-profile tasks. These are scenarios where a group collectively holds all the information needed to make a correct choice, but individual members only have pieces of the puzzle. Typically, information held by everyone (shared info) points to a "decoy" (a plausible but wrong choice), while the critical information needed to find the truth is "private" (held by only one person).

When we compress these discussions to fit into an LLM's context window, we usually rely on two heuristics:

  1. Rarity: Keep the facts that only one or two agents mentioned (assuming they are the "private" keys to the truth).
  2. Relevance: Keep facts that relate to the decision criteria.

The paper investigates why these heuristics fail and how the way we attribute information (who said what) biases the final decision-maker.

Methods

The researchers developed a pipeline to test how different "memory policies" affect decision accuracy across several LLMs (Qwen2.5-7B, Llama-3.1-8B, and DeepSeek models).

Figure 2: Pipeline. Facts from template M01 (Table 4) are distributed among the agents; HiddenBench tasks have three or four agents and CrossProfile tasks have four. After the discussion, a memory policy compresses it under a token budget B, either by summarizing the transcript (B3) or by selecting whole claims from a claim inventory (R1, R1-rel, B4, Random). A separate call with the same model weights answers from the task and the memory alone.

They compared several memory policies:

  • R1 (Rarest-first): Prioritizes facts mentioned by the fewest agents.
  • B4 (First-mention): Prioritizes facts based on when they first appeared in the transcript.
  • R1-rel (Relevance-first): Filters for facts relevant to the criteria, then applies the rarity rule.
  • B3 (Summary): An LLM-generated summary of the discussion.

Datasets

The study uses two main benchmarks:

  1. HiddenBench: An existing benchmark for multi-agent reasoning.
  2. CrossProfile (New): A diagnostic benchmark of 60 templates (480 tasks total). Unlike previous benchmarks, CrossProfile systematically "crosses" fact ownership. It takes the same set of facts and varies whether the "support" facts (pro-correct) or "decoy" facts (pro-wrong) are shared or private. This allows researchers to see if a model is actually following a rarity rule or just getting lucky because the rare facts happened to be the right ones.

Key Insights and Ideas

  • Rarity is a Gamble: Prioritizing rare facts only works if the rare facts are the useful ones. If the "decoy" facts are the ones held privately, the rarity heuristic leads the model straight to the wrong answer.
Figure 1: Rarity and decision usefulness. Fact text stays fixed while the ownership of support and decoy facts changes; here irrelevant facts stay private. Filled dots mark the agents holding each fact, and the boxes on the right show what rarest- first selection prioritizes. (c) The three ownership factors are crossed. Decoys are true, criterion-relevant facts that favor a competing option. Role labels are never shown to the models.
  • Relevance is Blind to Utility: Decoys are, by definition, relevant to the decision. A relevance filter cannot distinguish between a helpful fact and a misleading one that is "on topic."
  • The "Social Proof" Bias: LLMs exhibit a version of the human "common-knowledge effect." They give extra weight to facts attributed to many agents (e.g., marked with tags like [A1, A2, A3, A4]). This bias persists even when the "shared" facts are just redundant assignments, not independent observations.
  • The Upstream Bottleneck: In natural, unscripted discussions, agents often fail to even mention their private information. If the evidence never makes it into the transcript, no memory policy—no matter how clever—can recover it.

Key Results

  • Performance Reversal: On CrossProfile, the Rarest-first (R1) and First-mention (B4) policies are mirror images. R1 hits ~95% accuracy when support is private, but drops to ~20% when decoys are private.
Figure 3: Who wins depends on who holds what. CrossProfile accuracy at r = .6 by support and decoy ownership (each point averages the two irrelevant-fact assignments, 60 templates, three seeds). R1 and B4 are mirror images; R1-rel varies little across cells but falls well below R1 in the classic hidden-profile column (shaded: private support, shared decoys), where even the all-facts memory (dashed) drops. Per-cell intervals for Qwen and Llama are in Appendix A.2.
  • Social Proof Impact: Removing attribution tags from a memory containing all facts increased accuracy by 13 to 24 points in "classic" hidden-profile setups. This proves the model was being misled by the number of "speakers" associated with a fact, rather than the fact's content.
  • Natural Discussion Failure: In unscripted tests, the full transcript (REF) actually yielded lower accuracy than an empty memory. The models were effectively talking themselves into the wrong answer because they failed to disclose their private evidence.

Limitations and Future Work

The authors acknowledge that their study used a fixed group size (four agents) and focused on scripted vs. natural discussion gaps.

Future work should move away from simple prevalence-based or topic-based filtering. Instead, memory designs for agent groups should aim to preserve the balance of evidence between competing options. Furthermore, researchers suggest that system prompts should be carefully designed to ensure agents disclose private evidence before they start making recommendations, helping to solve the "upstream" silence that dooms many group decisions.

Summary updated

Abstract

When an LLM group's discussion is compressed into a short memory for a final decision maker, what should the memory keep? Two natural heuristics keep the rarest claims or the claims relevant to the decision criteria. On hidden-profile tasks both look attractive, because how widely a fact is held is confounded with whether it helps. We introduce CrossProfile, a diagnostic benchmark of 60 templates with automatically verified answer keys, in which the ownership of supporting, decoy, and irrelevant facts is crossed while their text is held fixed (480 tasks). Across Qwen2.5-7B, Llama-3.1-8B, and two DeepSeek models, both heuristics fail in predictable places. Selecting by relevance readmits decoys, because decoys are on topic: even a perfect relevance filter loses 23 to 31 points to rarest-first selection in the classic hidden-profile configuration. Rarest-first selection is no better than random selection on average and wins only where the rare facts happen to be the useful ones. In both cases accuracy follows the balance of evidence the memory keeps, not the policy that kept it. The decision model adds a third failure, a form of social proof: it gives extra weight to facts attributed to many agents. Removing the attribution tags, or reassigning them at random with line order fixed, raises accuracy in the classic configuration by 13 to 24 points. In natural discussions the evidence is lost before any memory acts: the complete transcript yields lower accuracy than no notes at all.
BibTeX
@misc{imel2026rare,
  author = {Anouar Imel and Imad Charradi and Abderrahman Sghir and Khalil El Khammar},
  title = {{Rare, Relevant, and Still Wrong: How Memory Fails LLM Group Decisions}},
  year = {2026},
  eprint = {2610.37624},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.37624},
}
Figure