The Efficiency Attenuation Phenomenon: A Computational Challenge to the Language of Thought Hypothesis

• URL: http://arxiv.org/abs/2603.22312v1
• Date: Thu, 19 Mar 2026 23:49:15 GMT
• Title: The Efficiency Attenuation Phenomenon: A Computational Challenge to the Language of Thought Hypothesis
• Abstract summary: We introduce the AI Private Language'' thought experiment.<n>If two artificial agents develop an efficient, inscrutable communication protocol, their performance declines when forced to use a human-comprehensible language.<n>Results show that agents with an emergent protocol achieve 50.5% higher efficiency than those using a pre-defined, human-like symbolic protocol.
• Score: 8.201374511929538
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper computationally investigates whether thought requires a language-like format, as posited by the Language of Thought (LoT) hypothesis. We introduce the ``AI Private Language'' thought experiment: if two artificial agents develop an efficient, inscrutable communication protocol via multi-agent reinforcement learning (MARL), and their performance declines when forced to use a human-comprehensible language, this Efficiency Attenuation Phenomenon (EAP) challenges the LoT. We formalize this in a cooperative navigation task under partial observability. Results show that agents with an emergent protocol achieve 50.5\% higher efficiency than those using a pre-defined, human-like symbolic protocol, confirming the EAP. This suggests optimal collaborative cognition in these systems is not mediated by symbolic structures but is naturally coupled with sub-symbolic computations. The work bridges philosophy, cognitive science, and AI, arguing for pluralism in cognitive architectures and highlighting implications for AI ethics.

Related papers

• The Era of Agentic Organization: Learning to Organize with Language Models [107.41382234213893]
  We introduce asynchronous thinking (AsyncThink) as a new paradigm of reasoning with large language models.<n> Experiments demonstrate that AsyncThink achieves 28% lower inference latency compared to parallel thinking.<n>AsyncThink generalizes its learned asynchronous thinking capabilities, effectively tackling unseen tasks without additional training.
  arXiv  Detail & Related papers  (2025-10-30T16:25:10Z)
• On the Same Wavelength? Evaluating Pragmatic Reasoning in Language Models across Broad Concepts [69.69818198773244]
  We study a range of LMs on both language comprehension and language production.<n>We find that state-of-the-art LMs, but not smaller ones, achieve strong performance on language comprehension.
  arXiv  Detail & Related papers  (2025-09-08T17:59:32Z)
• A Computationally Grounded Framework for Cognitive Attitudes (extended version) [14.866324473006255]
  We introduce a novel language for reasoning about agents' cognitive attitudes of both epistemic and motivational type.<n>Our language includes five types of modal operators for implicit belief, complete attraction, complete repulsion, realistic attraction and realistic repulsion.<n>We present a dynamic extension of the language that supports reasoning about the effects of belief change operations.
  arXiv  Detail & Related papers  (2024-12-18T17:17:07Z)
• Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents [80.5213198675411]
  Large language models (LLMs) have dramatically enhanced the field of language intelligence. LLMs leverage the intriguing chain-of-thought (CoT) reasoning techniques, obliging them to formulate intermediate steps en route to deriving an answer. Recent research endeavors have extended CoT reasoning methodologies to nurture the development of autonomous language agents.
  arXiv  Detail & Related papers  (2023-11-20T14:30:55Z)
• From Heuristic to Analytic: Cognitively Motivated Strategies for Coherent Physical Commonsense Reasoning [66.98861219674039]
  Heuristic-Analytic Reasoning (HAR) strategies drastically improve the coherence of rationalizations for model decisions. Our findings suggest that human-like reasoning strategies can effectively improve the coherence and reliability of PLM reasoning.
  arXiv  Detail & Related papers  (2023-10-24T19:46:04Z)
• Learnability with PAC Semantics for Multi-agent Beliefs [38.88111785113001]
  The tension between deduction and induction is perhaps the most fundamental issue in areas such as philosophy, cognition and artificial intelligence. Valiant recognised that the challenge of learning should be integrated with deduction. Although weaker than classical entailment, it allows for a powerful model-theoretic framework for answering queries.
  arXiv  Detail & Related papers  (2023-06-08T18:22:46Z)
• Neuro-Symbolic Causal Language Planning with Commonsense Prompting [67.06667162430118]
  Language planning aims to implement complex high-level goals by decomposition into simpler low-level steps. Previous methods require either manual exemplars or annotated programs to acquire such ability from large language models. This paper proposes Neuro-Symbolic Causal Language Planner (CLAP) that elicits procedural knowledge from the LLMs with commonsense-infused prompting.
  arXiv  Detail & Related papers  (2022-06-06T22:09:52Z)
• Learning to refer informatively by amortizing pragmatic reasoning [35.71540493379324]
  We explore the idea that speakers might learn to amortize the cost of Rational Speech Acts over time. We find that our amortized model is able to quickly generate language that is effective and concise across a range of contexts.
  arXiv  Detail & Related papers  (2020-05-31T02:52:22Z)
• Emergence of Pragmatics from Referential Game between Theory of Mind Agents [64.25696237463397]
  We propose an algorithm, using which agents can spontaneously learn the ability to "read between lines" without any explicit hand-designed rules. We integrate the theory of mind (ToM) in a cooperative multi-agent pedagogical situation and propose an adaptive reinforcement learning (RL) algorithm to develop a communication protocol.
  arXiv  Detail & Related papers  (2020-01-21T19:37:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.