General Intelligence

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 35

Sep 30, 2026cs.CV

PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop

Vision-Language Models (VLMs) have shown strong multimodal reasoning capabilities, yet whether they truly capture the physical consistency underlying real-world dynamics remains unclear. Existing benchmark paradigms often suffer from fragmented evaluation, focusing on isolated cognitive stages while overlooking the inherent synergy between perception, reasoning, and physical judgment. The lack of a holistic perspective limits the ability to diagnose whether VLMs can reliably evaluate the physical authenticity of emerging generative models. To address these issues, we introduce PhysVista, a benchmark designed to evaluate physical intelligence in VLMs through a closed cognitive loop framework inspired by the human seeing-reasoning-assessment process. PhysVista restores this loop by jointly evaluating physical state perception, physical dynamics reasoning, and physical plausibility assessment. It further distinguishes event-level reasoning and scale-level reasoning to enable fine-grained analysis of physical understanding. In addition, PhysVista incorporates both real-world and AI-generated videos, allowing evaluation across diverse domains and emerging generative scenarios. Extensive experiments across a diverse set of VLMs reveal substantial limitations in physical reasoning and plausibility assessment, highlighting a persistent gap between visual recognition and genuine physical understanding, and pointing toward more principled designs for physically grounded multimodal intelligence.

Xinge Peng, Yiting Lu, Tianwu Zhi +4

University of Science and Technology of China · ByteDance · City University of Hong Kong

Multimodal Reasoning Perception Pipeline General Intelligence Generative Models Loop

Sep 30, 2026cs.CV

GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives

Precise grounding matters. It specifies which object is the target and where that object is, even in clutter and for tiny objects, and it has to be fast enough for closed-loop control. Yet vision-language-action (VLA) and world-action models (WAMs) take perception from general-purpose vision-language and video-generation backbones, which still fail in these settings. We introduce GroundingPI, a 4B grounding foundation model that generates points and boxes as quantized coordinates in a shared vocabulary. Training combines multimodal and spatial pretraining, supervised fine-tuning, and reinforcement learning with GRPO, using supervision from public datasets and dedicated data engines. Against 44 baselines across 34 grounding benchmarks spanning 11 perceptual capabilities, GroundingPI establishes a new state of the art, averaging 73.68%, above the larger GPT-6 Astra (71.54%). As a downstream visual backbone, GroundingPI improves performance on robotic manipulation and autonomous driving. On RoboTwin 2.0, it outperforms every mainstream backbone we evaluate in all four out-of-distribution settings, by up to 24.8% relative to the strongest backbone. On RoboCasa-GR1, GroundingPI trained with 50% of the demonstrations outperforms those baselines trained with 75%. On nuScenes, used as the visual backbone, GroundingPI attains an average open-loop L2 error of 0.296 m. We systematically analyze GroundingPI's pretraining in scale and data composition. Downstream autonomous driving and robotic manipulation improve as the pretraining is scaled. Analyzing the data recipe across these 11 perceptual capabilities shows dense grounding's substantial benefits for both, and OCR's potential as a catalyst for perceptual learning. These results support grounding as a perceptual foundation, and dedicated perceptual pretraining as a promising direction for foundation models of physical intelligence.

Qize Yu, Lianrui Fan, Boyu Chen +23

XPeng Inc. · Peking University · The University of Hong Kong +4

Diffusion-Based Vision-Language-Actions Grounding Robotic Manipulation Foundation Model General Intelligence

Sep 27, 2026cs.AI

Temporal Graph Learning of Wearable Actigraphy and Sleep Traces for Modelling Adolescent Crystallized Intelligence

Wearable actigraphy offers a scalable, ecologically valid alternative to episodic clinical assessment. However, predicting continuous adolescent crystallized intelligence (

G_c

) from such traces remains challenging due to irregular device adherence and complex behavioral-environmental interactions. We address this using daily summary data derived from 21-day Fitbit records of 6,091 adolescents in the Adolescent Brain Cognitive Development Study (Release 5.1). We propose SATURN, a Sleep-Activity Temporal Unified Regression Network. It represents participants as 21-node temporal graphs encoding daily behaviors and temporal adjacency. To prevent imputation artifacts, invalid-day edges are dynamically pruned during forward passes. Node embeddings are refined via residual GATv2 layers, aggregated through masked attention pooling, and fused with sociodemographic covariates. Under family-controlled, age-sex-BMI-stratified cross-validation, SATURN achieves

R^2 = 0.2783 \pm 0.0127

, consistently improving upon flattened machine learning (Gradient Boosting,

R^2 = 0.2372

) and sequential deep learning (BiLSTM,

R^2 = 0.2688

) baselines. Explainability analyses identify light activity, metabolic equivalents, and sleep duration as dominant predictors, while Monte Carlo dropout and subgroup analyses confirm equitable performance across sociodemographic strata. Ultimately, SATURN establishes a rigorous computational framework for digital cognitive phenotyping, offering a scalable pathway to complement traditional assessments by highlighting macro-level behavioral anomalies.

Md. Tanvir Rahman, Nabil Anan Orka, Asaduzzaman Khan +1

School of Health and Rehabilitation Sciences, The University of Queensland, QLD 4072, Australia

Sleep General Intelligence Temporal Graph Neural Networks Human Activity Recognition

Sep 23, 2026cs.LG

Policy Complexity, Reaction Time, and Bounded Rationality in Reinforcement Learning

Biological agents do not learn under conditions of unlimited computation. For humans, learning and choice are shaped by constraints on perception, attention, and working memory, which limit how much state information guides behavior and therefore bound policy complexity. Standard reinforcement learning models typically optimize reward without explicitly representing these internal costs, making them less suitable as models of biological intelligence. We derive MI-SARSA, an on-policy temporal-difference algorithm that incorporates mutual-information regularization through a learned marginal action prior and a penalty on state-specific deviations from that prior. This yields a sequential learning model in which state information is used selectively when its expected return benefit justifies the added informational cost. Critically, the same state-specific information cost that governs policy compression also generates trial-level predictions for reaction time, distinguishing MI-SARSA from most reinforcement learning models, which predict choices or returns but not latency. Empirically, MI-SARSA produces a reward-complexity tradeoff, and stronger information penalties produce simpler policies with lower control costs and faster reaction times. Under environment shift, increasing regularization reduces post-switch performance degradation but also lowers asymptotic return, revealing a robustness-capacity tradeoff. Together, these results position MI-SARSA as a model of bounded sequential learning under cognitive constraints.

James Wu, Chris R. Sims

Department of Computer Science Rensselaer Polytechnic Institute Troy, NY, 12180 · Department of Cognitive Science Rensselaer Polytechnic Institute Troy, NY, 12180

Rationality General Intelligence Regularization

Sep 22, 2026cs.RO

Intelligence Across Embodiments

Robotic embodiment encompasses the sensing, kinematics, dynamics, geometry, actuation, and control through which an agent physically interacts with the world. These properties vary across robots and change over time. We argue that general embodied intelligence requires learning that accumulates across these differences. Prevailing methods that engineer correspondences to bridge embodiment differences offer immediate practical gains, but their assumptions limit the scope of transfer in the long run. Instead, a more general approach should discover representations that support transfer to a larger range of embodiments as experience grows. We propose embodiment diversity as a promising axis of scaling, and identify broad learned priors as a complementary ingredient. We call for evaluations that better characterize embodiment gaps and transfer performance. More broadly, cross-embodiment learning connects the practical challenge of learning from heterogeneous robot experience with a broader scientific pursuit inspired by nature - physical intelligence that adapts and co-evolves with its embodiments to gain agency over its behavior and physical forms.

Bo Ai, Henrik I. Christensen, Hao Su

Stanford University · University of California San Diego · Sudo AI GmbH

Cross-Embodiment Transfer Embodiment Heterogeneous Robot Teams Robotic Systems General Intelligence

Aug 31, 2026cs.LG

Flawed in Nature, Perfect through Evolution

The performance of artificial intelligence (AI) and machine learning (ML) models degrades when the problem they were trained on drifts. This is a near-universal feature of real-world problems, which often change unpredictably. Biological evolution has achieved intelligence by overcoming this obstacle through natural selection acting on heritable variation. AI/ML techniques have long incorporated forms of natural selection, but it has been challenging to maintain model diversity as optimization naturally drives convergence. Here we show that a swarm of AI/ML models subjected to deliberate mutations of their model coefficients away from optimality can reliably and sustainably improve performance in changing environments by acting as a statistical hedge against non-stationarity. We call this mechanism 'Flawed in Nature, Perfect through Evolution', reflecting that the collective performance gain goes at the expense of individual performance. We prove via four theorems that the resulting regret reduction is guaranteed under general conditions, establishing the Flawed-in-Nature mechanism as a generalizable design principle for AI/ML systems. We validate these results on synthetic linear regression tasks, demonstrating that the mutated swarm delivers the best model in

\sim80\%

of environment changes and that inference synthesis successfully translates this individual advantage into a collective one. The mechanism proves to be most effective when the mutation drift rate matches the drift rate of the environment. We outline a simple, adaptive controller that enables practical applications by tuning the mutation drift rate to match the unknown drift rate of the environment. The close analogy of the Flawed-in-Nature mechanism to biological evolution suggests it may have been a critical missing ingredient for the organic discovery of AI forms that more closely mimic biological intelligence.

J. M. Diederik Kruijssen

Allora Foundation

Evolutionary Optimization Methods General Intelligence

Aug 11, 2026cs.CY

Smart Enough to Go Extinct? An Evolutionary Challenge to the Value of General Intelligence and Its Ethical Implications for AGI

The pursuit of artificial general intelligence (AGI) rests on a seemingly self-evident premise: that general intelligence, the kind of flexible, domain-general cognitive capacity exemplified by Homo sapiens, is extraordinarily valuable. This paper subjects this premise to critical scrutiny. We first present the intuitive case for the value of general intelligence before mounting an evolutionary challenge. We argue that, on evolutionary timescales, its adaptive value is far from empirically established. Numerous taxa, from cyanobacteria to horseshoe crabs, have persisted for hundreds of millions or even billions of years without anything resembling general intelligence, while Homo sapiens has existed for roughly 300,000 years and already faces self-generated existential risks. Mass extinction events do not preferentially favour cognitively sophisticated species. We argue that general intelligence may be the only biological strategy that generates existential threats to the species possessing it, an existential risk paradox with no parallel among non-intelligent survival strategies. Unlike prevailing accounts of AI risk that trace the danger to misalignment, we locate it in structural features of general intelligence itself, implying that even well-aligned AGI would inherit this liability. If the long-term evolutionary value of general intelligence is uncertain or negative, this raises ethical questions about engineering AGI and, more urgently, creating artificial consciousness. Drawing on deontological ethics and the precautionary principle, we argue that this uncertainty imposes a duty of caution: if we create a new kind of intelligent being, we bear responsibility for ensuring the conditions under which it can flourish.

David Klotz

Hochschule der Medien Stuttgart

General Intelligence Ethics Artificial Intelligence Systems Evolutionary Optimization Methods Biological

Jul 21, 2026cs.AI

Athena-Brain Technical Report: An Efficient Robot Brain for General Intelligence and Embodied Interaction

Large language models (LLMs) have demonstrated remarkable capabilities in language understanding, reasoning, and world knowledge. As embodied agents become increasingly capable, there is a growing demand for compact models that can serve as an on-device brain, preserving the broad general intelligence of LLMs while enabling effective high-level interaction with embodied environments. Existing approaches, however, often prioritize either general-purpose intelligence or specialized embodied capabilities, making it challenging to satisfy both requirements within a single model. We present \textbf{Athena-Brain-8B}, an 8B LLM designed to serve as an on-device brain for embodied intelligence for embodied intelligence. Through a multi-stage post-training pipeline consisting of General Supervised Fine-Tuning, General Reinforcement Learning, Embodied Expert training, and Model Merge, Athena-Brain-8B maintains strong general capabilities while acquiring strong high-level embodied interaction capabilities and generating concise responses for efficient embodied interaction. Experimental results demonstrate the effectiveness of Athena across both general and embodied evaluations. Compared with the corresponding Qwen3-8B thinking model, Athena-Brain-8B achieves comparable performance on general language and reasoning benchmarks while generating substantially shorter responses. On in-domain embodied benchmarks, Athena-Brain-8B consistently outperforms models of similar scale and surpasses several substantially larger frontier models evaluated zero-shot, demonstrating that compact language models can effectively integrate strong general intelligence with embodied capabilities.

Jialian Li, Junhong Liu, Yuchen Cao +6

XPENG ROBOTICS

Embodied Artificial Intelligence Embodied General Intelligence Reasoning Benchmark Offline Reinforcement Learning

Jul 21, 2026cs.AI

What General Intelligence Requires: Non-Reducible Constraints Across Levels of Description

General intelligence, of the kind that underwrites the full range of human cognitive achievement, is not a property of computational architecture alone. This paper advances a single thesis: the structural constraints on general intelligence occupy distinct levels of description and are mutually non-reducible, in the sense that the special-sciences tradition gives to that term. It follows that no single architectural advance, and no continuation of the scaling programme by itself, can produce artificial general intelligence (AGI), and that research programmes must be evaluated against the full constraint profile rather than against performance on any one benchmark. The thesis is developed through a method that reads general intelligence through four evidential lenses, AI systems research, anthropology, law, and economics, each anchored to a distinct level of description, supplemented by speculative fiction used as a disciplined heuristic in the context of discovery rather than the context of justification. Applying the method yields a taxonomy of twenty-three structural constraints organised into eight clusters; six are examined in depth and ordered as an ascending ladder of levels, with explicit bridges showing why progress at one level cannot carry to the next. The argument issues in five falsifiable predictions, each stated with a named benchmark family and a disconfirmation condition, converting a descriptive framework into a research programme with a longer horizon than the scaling hypothesis implies.

Subhomoy Bakshi

Lakshmikumaran and Sridharan Attorneys, New Delhi, India

General Intelligence Artificial Intelligence Systems Cognitive Science Structural Constraints Hypothesis

Jul 18, 2026cs.RO

PhyAgentOS: A Self-Evolving Operating System for Embodied Agents with Decoupled Cognitive Planning and Physical Execution

Vision-language-action models, world models, and agentic planners each advance physical intelligence, yet their composition lacks a common execution abstraction, shared state, semantic verification, and persistent experience across heterogeneous embodiments. We present PhyAgentOS, a runtime foundation delivering scheduling, verification, memory, benchmarking, and safety as system-level services. Its Session-Centered Runtime treats a session, not an action, as the minimum unit of scheduling, compatibility preflight, supervised execution, evidence collection, and acceptance. To decouple cognition from physical execution, the cognition-physics boundary is a file system: the State-as-a-File protocol materializes cross-layer state as Markdown with YAML, yielding inspectable, versionable records without code dependencies between Agent and Runtime layers. These views form a unified cognitive state space aligning intent, capabilities, environment, execution, and experience. The SessionVerifier distinguishes execution termination from semantic task completion via evidence-grounded verdicts of success, failure, or replan. Verified outcomes are consolidated through epistemic memory into reusable knowledge and corrective lessons, closing a trial-and-error loop without retraining. Benchmarking reuses the deployment session and verification path, so results trace to real execution. Layered safety constrains both policy-driven and agent-driven execution: preflight, action bridges, SafetyGuard, heartbeat monitoring, and target-local constraints. Validation is progressive: games test cognitive planning, simulation adds dynamics and control, real robots add hardware noise, with the cognitive layer held constant. PhyAgentOS is benchmarked on Optimus-67, StarDojo, and DST-Dojo, validated on 19+ simulated and physical embodiments, and gains on LIBERO, Calvin, and RoboCasa365 across multiple VLA models.

Yang Liu, Weixing Chen, Xinshuai Song +8

1X-Era Lab · 2HCP Lab, Sun Yat-sen University · 3Peng Cheng Laboratory

Embodied Agents Runtime Enforcement General Intelligence Cognitive Science

Jul 18, 2026cs.AI

FST.ai 2.5: Explainable and Uncertainty-Aware AI for Olympic and Para-Taekwondo Decision Support, Athlete Digital Twins, and Federation-Scale Analytics

The rapid digitalisation of elite sport has created new opportunities for integrating artificial intelligence (AI), performance analytics, and decision-support systems into athlete development and competition management. However, existing solutions remain fragmented, typically addressing isolated tasks such as performance analysis, athlete monitoring, or referee support. This paper presents \textbf{FST

\cdot

ai~~2.5}, an explainable, uncertainty-aware, and secure AI framework for Olympic and Para-Taekwondo. \textbf{FST $\cdot$ ai~~2.5} introduces a unified digital ecosystem integrating athlete intelligence, competition analytics, federation-scale data management, AI-assisted decision support, athlete and event digital twins, explainable performance indicators, and adaptive training recommendations. The framework supports World Taekwondo (WT), Member National Associations (MNAs), coaches, referees, analysts, and athletes through transparent, secure, and federation-aware governance. By combining multi-source competition data, athlete-performance information, and contextual evidence, \textbf{FST

\cdot

ai~2.5} provides tactical diagnostics, longitudinal athlete monitoring, performance forecasting, personalised development planning, and federation-wide benchmarking using explainable and uncertainty-aware AI. Prototype deployments demonstrate the feasibility of the proposed framework. Although developed for Olympic and Para-Taekwondo, the methodology is broadly applicable to explainable AI, digital twins, and trustworthy decision support in combat sports and other high-performance sporting environments.

Keivan Shariatmadar, Ahmad Osman, Ramin Rey

AutomaTiQ Research Group, htw saar University of Applied Sciences and Fraunhofer IZFP, Saarbrücken, Germany · 2Sport Director, Austrian Taekwondo Union (ATU)

Digital Twins Ai-Based Framework Software Engineering Decision Support General Intelligence

Jul 17, 2026cs.CV

Apple- $π$ : Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence

Modern video generation models are increasingly hailed as emerging world models with an internalized grasp of physical law. Yet existing benchmarks largely evaluate physical plausibility only at the output level, without verifying whether the model arrives there through a faithful, law-grounded reasoning process. We introduce Apple-PI, the first benchmark that anchors video-model evaluation explicitly in physical laws. Apple-PI comprises three components. 1) Orchard: a dataset of 400 videos covering ten canonical tasks in classical mechanics. It separates single-law tasks for confounder-free diagnosis from multi-law tasks for probing generalization. 2) Benchmark Protocol: a three-stage protocol based on scientific reasoning, including Perception, Formulation, and Deduction. It uses chain-of-frames prompting on infographic-annotated first frames, treating the generated video as the model's visible reasoning trace. 3) Evaluation Suite: a hybrid evaluation suite that combines MLLM-based subjective scoring with physics-law-grounded objective measures. This enables stage-resolved diagnosis of not only whether a model fails, but where it fails. Benchmarking 11 models shows that current video models remain far from reliable law-grounded world simulators, with the best video model scoring only 0.473. Our stage-, pillar-, and source-resolved analyses further expose a Perception-to-Formulation-to-Deduction bottleneck, weak multi-law state transfer, and a persistent Sim-to-Real gap. These findings position Apple-PI as a diagnostic foundation for guiding future video models toward world models with law-grounded physical intelligence.

Runmao Yao, Kairui Hu, Yukang Cao +11

1S-Lab, Nanyang Technological University · 2The Chinese University of Hong Kong

Generative Video Models Physical Plausibility General Intelligence

Jul 16, 2026cs.RO

Towards Human-like Physical Intelligence: LifelongVision-Language-Action Learning for Robotic Manipulation

Similar to the natural capabilities of humans to sequentially learn new tasks, robots with Vision-Language-Action (VLA) models should possess lifelong learning ability to learn a new task when deployed in open-world environments. However, most recently proposed lifelong learning models aim to effectively learn the current task (plasticity) or maintain high accuracy on previous tasks (stability), while the plasticity-stability trade-off remains largely unsolved in robotic manipulation models. To address this fundamental challenge, we propose a cache-efficient lifelong Vision-Language-Action learning framework for robotic manipulation (i.e., LifelongVLA), which alleviates the plasticity-stability trade-off with a dual-timescale adaptation mechanism while achieving low-cost robotic deployment with a cache-efficient replay strategy. More concretely, we propose a dual-timescale LoRA gating module to decompose VLA adaptation into two lightweight pathways: a short-term adapter for plasticity and a long-term adapter for stable consolidation. These pathways are integrated via a task-aware gate, enabling explicit control of the plasticity-stability trade-off. In the skill replay phase, a cache-efficient stochastic replay strategy is proposed to preserve more balanced retention signals without full-trajectory storage. Finally, experiments show that LifelongVLA outperforms existing baselines, demonstrating efficient skill expansion, robust retention of learned manipulation behaviors, and reduced reliance on retraining for real-world deployment on an xArm robot.

Yao He, Gan Sun, Wenqi Liang +2

South China University of Technology · University of Trento

Diffusion-Based Vision-Language-Actions Vision-Language-Action Framework Robotic Manipulation Plasticity Continual Learning General Intelligence

Jul 13, 2026cs.RO

From World Action Models to Embodied Brains: A Roadmap for Open-World Physical Intelligence

Artificial general intelligence ultimately requires agents that can reason and act in the physical world. Action models, vision-language-action policies, and world models have advanced this goal, while World Action Models (WAMs) are particularly promising because they connect candidate interventions with predicted consequences. However, progress remains fragmented: models use incompatible action spaces and prediction targets, datasets and tasks follow different conventions, and runtime systems expose limited interfaces for reuse and evaluation. We review the evolution toward WAMs and organize these limitations into three coupled gaps: model roles and representations, objectives and standardization, and system composition. Building on this analysis, we propose a co-evolution roadmap for physical intelligence centered on the \emph{embodied brain}, a long-term model target for integrating multimodal context, comparing candidate interventions, and issuing state-transition or capability requests rather than direct actuator commands. WAMs provide promising prototypes for its predictive functions, while a physical harness grounds model outputs through tools, controllers, verification, and trace logging. Shared contracts align heterogeneous models, data, tasks, and embodiments, and closed-loop post-training converts verified interaction into reusable experience. Together, these components define a modular physical-intelligence stack for adaptive and self-improving embodied agents.

Yuanzhi Liang, Xufeng Zhan, Haibin Huang +2

Embodied Artificial Intelligence World Models General Intelligence Embodiment Artificial Intelligence Systems Roadmap+1

Jul 13, 2026cs.AI

Bringing Back Rule Induction to Fluid Intelligence Research? An Initial Validation of the ARC-AGI Benchmark in Humans

Two competing perspectives on fluid intelligence (gf) measures propose that performance is primarily constrained either by working memory capacity or by the ability to induce novel relations. The first perspective is currently dominant in measurement, as evident from the use of a limited set of recurring rules, whereas the second perspective is reflected in many definitions but rarely present in measurement. The ARC-AGI benchmark predominantly requires rule induction and was proposed as a measure of gf for both humans and artificial systems. However, its psychometric properties have not yet been examined in human samples. We therefore investigated the psychometric characteristics and nomological network of ARC-AGI in a first study with 100 participants. A compilation of ARC-AGI items showed good psychometric properties and correlated substantially with figural fluid intelligence as measured by a figural reasoning test (

ρ

= .63). Associations with figural originality were weak. These findings provide initial support for the validity of ARC-AGI as a measure of human fluid intelligence. Future research should include more rule induction tasks as well as additional multivariate covariates. This study is unusual by studying a task in humans that was initially designed for machines. We suggest systematically embedding AI benchmarks into the nomological network of human cognitive abilities to enable more systematic evaluation and interdisciplinary cooperation.

Jasmin Thelen, Oliver Wilhelm

Institute of Psychology and Education, Ulm University, Germany

General Intelligence Psychometric Properties Intelligence Induction Visual Reasoning

Jul 8, 2026cs.AI

Measuring Intelligence Beyond Human Scale

How can we measure intelligence beyond human capability? Human-authored benchmarks saturate, and above human capability, examiners may not know which tasks are both hard and verifiable. We argue that this difficulty is inherent to absolute-scale evaluation and propose a new paradigm based on relative measurement in which models generate public challenges that separate other systems. Aggregating these outcomes yields an adversarial psychometric rating system that can scale with the systems being measured. We describe practical protocols that reduce incentives for private-information attacks, support judge-free adjudication, and naturally scale with agent capabilities. We instantiate the framework across verifiable and open-ended, non-verifiable domains, illustrating how model-generated evaluation can continue to measure systems beyond the human frontier.

Jerry Han, Rafael Moschopoulos, Ella Colby +5

Princeton Superalignment

General Intelligence Psychometric Properties Intelligence Relative Position

Jul 7, 2026cs.AI

Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment

Vision-language models (VLMs) struggle to generalize in interactive physical reasoning, particularly under unseen tasks and environments. Two key failure modes are prominent: hallucinated chain-of-thought (CoT) reasoning that contradicts physical reality, and misalignment between the model's reasoning and actions. We present VAORA (Visual Action Outcome Reasoning Alignment), a novel reward design that directly addresses both issues. VAORA introduces two complementary rewards: Visual Alignment Reward, which anchors VLM reasoning to the visual context independent of the agent action itself, and Visual-Action Alignment Reward, which grounds reasoning in the visual outcome induced by the model's action. Together, these rewards suppress hallucinated CoT and reduce the gap between reasoning and behavior. To improve training stability, we further employ smooth, dense rewards by estimating success probabilities using a pre-trained in-domain expert agent. Experiments on PHYRE and Virtual Tool support our performances across novel-task and unseen-environment settings, confirming that grounded and generalizable physical intelligence can be induced through VAORA.

Han-Jun Ko, Jr-Jen Chen, Haobo Yuan +4

National Taiwan University · The University of California, Merced

Visual Reasoning General Intelligence

Jul 1, 2026cs.CL

AGC-Bench: Measuring Artificial General Creativity

Creativity research has debated whether creativity is domain-specific (e.g., visual, writing, science), and if it is psychometrically separable from general intelligence. Both questions now apply to LLMs, but a unified benchmark of AI creativity remains elusive. We introduce AGC-Bench, an artificial general creativity benchmark built from a systematic review of the AI creativity literature (3,101 papers screened, 497 benchmarks identified), paired with an agentic harness that converts idiosyncratic codebases into HELM-standardized benchmarks. The first release covers 78 datasets spanning brainstorming, problem solving, STEM, narrative, figurative language, and humor. To address bias in LLM-as-judge, we apply Judge Response Theory -- a psychometric calibration of judge leniency/severity; we then fine-tune Qwen3-30B on the bias-corrected ratings of three frontier LLMs to produce AGC-Judge, an open-weight model that robustly scores new creativity benchmarks it was not trained on. Results reveal frontier models at the top of the AGC-Bench leaderboard, with open models close behind. LLMs show different creative strengths, ranking higher on some domains (e.g., writing) than others (e.g., scientific ideation). Extensive experiments yield three main findings. First, applying factor analysis across 83 LLMs, we recover a single creativity factor 'c', analogous to the 'g' factor of general intelligence, that explains 81.5% of variance, related to but separable from general knowledge/reasoning. Second, we show that prompting models to "be creative" boosts their performance far more than enabling reasoning, evidence that the benchmark tracks creativity over general ability. Third, on a human-matched subset, we find the top human still leads the top LLM on creativity. We release AGC-Bench with a public leaderboard, AGC-Judge, and human data as open infrastructure for measuring AI creativity at scale.

Roger Beaty, Vijeta Deshpande, Clin K. Y. Lai +9

1Pennsylvania State University · University of Massachusetts Lowell · University of Amsterdam +2

Creativity General Intelligence

Jun 18, 2026cs.AI

Thermodynamic Measure of Intelligence

Can intelligence be measured? We propose that intelligence can be defined as the lawful amplification of rare but valid futures: a system increases the probability of outcomes that would be unlikely under passive dynamics but remain admissible under the constraints of the domain. We start with the premise that an intelligent system must model the world and its own place within it. Because the system is part of the world it models, this leads naturally to recursive self-simulation: the system represents futures in which its own actions are part of the trajectory. Our central results give a necessity statement and a conditional near-sufficiency statement connecting this architecture to a precise thermodynamic measure of lawful amplification of rare-valid futures: high rare-valid lift is impossible unless the internal simulation identifies rare-valid futures with high fidelity; conversely, when rare-valid fidelity is high and the simulation contains an effective policy, the achievable lift approaches the actuation-limited optimum. Thus recursive self-simulation is not merely a plausible feature of intelligence but, under the stated assumptions, is necessary and nearly sufficient for high thermodynamic intelligence. The resulting framework makes intelligence measurable on a universal scale, from passive matter and feedback controllers, large language models, and humans as text generators to Maxwell-demon-like information engines.

Ishanu Chattopadhyay

Institute for Biomedical Informatics, University of Kentucky, Lexington, Kentucky, USA · Department of Computer Science, University of Kentucky, Lexington, Kentucky, USA

General Intelligence Intelligence Thermodynamics Passive

Jun 13, 2026cs.LG

A Compositional Framework for Open-ended Intelligence

Open-ended intelligence is the capacity to adapt to novel problems and environments that are substantially different from those in training. A mathematics of open-ended intelligence requires two pillars: first, a minimal set of representational primitives (e.g., states, actions) and algorithmic primitives (e.g., nearest neighbor); and second, an acquired compositional grammar for selection, recursion, and branching that produces sequences of operations and recurring motifs. We formalize open-ended intelligence in terms of the compositional closure induced by a finite primitive set

P

and a set of composition operators

C

. We characterize properties of the induced closure

\mathcal{L}(P,C)

that support unbounded compositional generation across families of tasks and worlds. The closure of the two pillars yields infinite adaptive responses across a wide range of settings. The mathematics supports complementary research agendas, including evaluation metrics for explanation and interpretability, and novel architectures where compositional generalization is native. We propose next primitive prediction (NPP) as a novel architectural objective, where training encourages the acquisition of reusable algorithmic primitives and their compositional grammar, such that new solutions are generated through recombination. Given such an objective, curriculum learning and self-play can enable lifelong learning, expanding the closure by discovering reusable primitives and transition motifs across settings. We ground the framework through case studies in physics, evolution, and neuroscience.

Ida Momennejad, Roberta Raileanu

Microsoft Research NYC, New York, USA · Google DeepMind, London, UK.

Compositional Generalization General Intelligence Intelligence Closure

Jun 9, 2026cs.RO

Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models

We introduce Embodied-R1.5, a unified Embodied Foundation Model (EFM) that integrates comprehensive embodied reasoning capabilities, spanning embodied cognition, task planning, correction, and pointing, within a single architecture toward general physical intelligence. Leveraging three automated data construction pipelines to significantly expand the data coverage of critical capabilities, we build a large-scale data system of over 15B tokens, and design a multi-task balanced RL recipe to alleviate heterogeneous task conflicts. We further introduce a Planner-Grounder-Corrector (PGC) closed-loop framework that enables a single model to autonomously execute and self-correct over long-horizon tasks. With only 8B parameters, Embodied-R1.5 achieves SOTA on 16 out of 24 embodied VLM benchmarks, surpassing leading models like Gemini-Robotics-ER-1.5 and GPT-5.4. Benefiting from the internalized embodied capabilities, Embodied-R1.5 can be fine-tuned into a VLA with only a small amount of data, outperforming leading VLA models like

π_{0.5}

across 4 popular manipulation benchmark suites. We further conduct extensive zero-shot real-robot experiments, validating performance in instruction following, affordance grounding, articulated object manipulation, and long-horizon complex tasks, demonstrating strong generalization to the physical world. We open-source model weights, datasets, training code, and EmbodiedEvalKit, an evaluation framework tailored for embodied tasks, to facilitate future research in EFMs.

Yifu Yuan, Yaoting Huang, Xianze Yao +20

Tianjin University · Tencent Hunyuan

Embodied Artificial Intelligence Embodied Wireless Foundation Models General Intelligence

May 27, 2026cs.AI

Measuring Progress Toward AGI: A Cognitive Framework

Despite widespread discussion of AGI, there is no clear framework for measuring progress toward it. This ambiguity fuels subjective claims, makes it difficult to track progress, and risks hindering responsible governance. As a starting point to address this gap, we present a framework for understanding system capabilities in relation to human cognitive abilities. Drawing from decades of research in psychology, neuroscience, and cognitive science, we introduce a Cognitive Taxonomy that deconstructs general intelligence into 10 key cognitive faculties. We then propose a rigorous evaluation protocol in which a system's performance is measured across a suite of targeted, held-out cognitive tasks, generating a 'cognitive profile' that can be used to understand a system's strengths and weaknesses. We hope this framework will provide a practical roadmap and an initial step toward more rigorous, empirical evaluation of AGI.

Ryan Burnell, Yumeya Yamamori, Orhan Firat +10

1Google DeepMind

General Intelligence Cognitive Science Artificial Intelligence Systems Taxonomy Evaluation Protocols

May 25, 2026cs.CL

BC Protocol: Structured Dual-Expert Dialogue for Eliciting High-Quality Chain-of-Thought Post-Training Data

High-quality expert chain-of-thought (CoT) data is one of the core bottlenecks in large language model (LLM) post-training. Existing data production methods each have structural limitations: crowdsourced annotation lacks deep reasoning paths; expert solo writing is constrained by the "expert blind spot" -- experts structurally skip reasoning steps they consider obvious; RLHF only produces preference signals rather than reasoning chains. This paper proposes the BC Protocol -- a structured dual-expert elicitation method for LLM post-training data production. The method carefully pairs a domain expert (crystallized intelligence) with a knowledge engineer (fluid intelligence), systematically externalizing the expert's implicit judgments as natural language reasoning chains. We introduce the Participant Aptitude Model, which defines six participant characteristic dimensions that affect elicitation quality. "Calibrated Ignorance" is an original concept proposed in this paper. We further propose "Selection-over-Prescription" as a methodological principle: for implicit knowledge elicitation tasks, investing quality-control resources in personnel selection yields a higher return than investing the same resources in process design. In a controlled experiment in the narrative fiction domain, we directly compared CoT produced by BC Protocol dual dialogue (Group A, (n=20)) against CoT written independently by the same domain expert (Group B, (n=20)). Three cross-vendor judge models -- GPT-4o, Claude Opus 4.5, and Gemini 2.5 Pro -- conducted blind evaluation across five dimensions (600 ratings total). Results show that the BC Protocol achieves an overwhelming advantage in "naturalness of reasoning process" (Group A mean 4.80 vs. Group B mean 1.30, (p=2.4\times10^{-8}), Cliff's (δ=1.0)).

Bo Zou, Chao Xu

LLM Reasoning Strategies Elicitation Reasoning Chain Post-Training Narratives General Intelligence+1

May 21, 2026cs.AI

Towards a General Intelligence and Interface for Wearable Health Data

While ubiquitous wearable sensors capture a wealth of behavioral and physiological information, effectively transforming these signals into personalized health insights is challenging. Specifically, converting low-level sensor data into representations capable of characterizing higher-level states is difficult due to high phenotypic diversity and variation in individual baseline health, physiology, and lifestyle factors. Moreover, collecting wearable data paired with health outcome annotations is laborious and expensive, and retrospective annotation remains practically unfeasible, contributing to a scarcity of data with high-quality labels. To overcome these limitations, we propose a foundation model for wearable health that is pretrained on more than one trillion minutes of unlabeled sensor signals drawn from a large cohort of five million participants. We demonstrate that the joint scaling of model capacity and pretraining data volume leads to systematic improvements in performance, as evaluated on a diverse set of 35 health prediction tasks, spanning cardiovascular, metabolic, sleep, and mental health, as well as lifestyle choices and demographic factors. We find that this population scale representation unlocks label-efficient few-shot learning and generative capabilities for robust daily metric estimation. To further leverage this learned representation, we deploy a classroom of LLM agents to autonomously search the space of downstream predictive heads built on the model embeddings, showing broad performance improvements that increase with LLM model capacity. Finally, we show how integrating these downstream predictors into a Personal Health Agent can support model responses that are more relevant, contextually aware, and safe, and we validate this via 1,860 ratings from a cohort of clinicians.

Girish Narayanswamy, Maxwell A. Xu, A. Ali Heydari +37

1Google Research · University of Washington · University of Illinois Urbana-Champaign +2

Wearable Physiology Wearable Devices Few-Shot Learning General Intelligence

May 16, 2026cs.AI

Artificial Adaptive Intelligence: The Missing Stage Between Narrow and General Intelligence

Between the narrow systems we deploy and the general intelligence we speculate about lies an entire regime of machine behavior that has never received its own name. This monograph argues that this regime is not empty: it is where meta-learning, neural architecture search, AutoML, continual learning, evolutionary computation, and physics-informed modeling have quietly converged on a common principle, namely the steady removal of the human from the loop of parameter specification. We name this regime Artificial Adaptive Intelligence (AAI) and define it operationally: a system exhibits AAI to the extent that it requires no human-specified tunable hyperparameters while maintaining competitive performance across a diverse distribution of tasks. To make the definition quantitative, we introduce an adaptivity index that measures progress along an axis orthogonal to scale, combining the fraction of hyperparameters absorbed by the system with the performance ratio against a task-specialized baseline. We develop the principle of parametric minimality and ground it in the minimum description length framework, showing that the appropriate hyperparameter count is data-determined rather than designer-determined. We then organize the field around three pathways to minimality: data- and task-aware configuration, structural and evolutionary morphing, and in-training self-adaptation. We analyze their stability, convergence, and governance implications, and illustrate them through case studies spanning aerospace design, financial regime detection, turbulence modeling, ecological dynamics, and vision-language systems. The thesis is that the path from ANI to AGI passes through AAI, and that naming this stage changes what we measure, what we build, and what we call a success.

Boris Kriuk

Artificial Intelligence Systems General Intelligence

May 15, 2026cs.RO

MyoChallenge 2025: A New Benchmark for Human Athletic Intelligence

Athletic performance represents the pinnacle of human motor intelligence, demanding rapid choices, precise control, agility, and coordinated physical execution. Replicating this seamless combination of capabilities remains elusive in current artificial intelligence and robotic systems. Concurrently, understanding the biological mastery of these movements is hindered because complex muscle coordination is rarely measured in vivo due to the limitations of physical equipment. To bridge this fundamental gap in understanding, MyoChallenge at NeurIPS 2025 established a pioneering benchmark for motor control intelligence in sports, leveraging high-fidelity musculoskeletal models within physics simulation combined with machine learning-driven algorithms. The competition introduces two distinct tracks emphasizing either upper or lower limbs control: a table tennis rally task utilizing a biomechanic upper limb composed of an arm with a hand and a trunk; and a soccer penalty kick using a biomechanic model of legs and a trunk. Marking the fourth iteration of the MyoChallenge series, this event attracted almost 70 teams and over 560 submissions globally, uniting a diverse community ranging from physicians and neuroscientists to machine learning experts. The competition facilitated the development of several state-of-the-art control algorithms for a musculoskeletal system capable of sports agility, leveraging techniques such as physics-based motion planners, on-policy behaviour cloning, hierarchical planning, and muscle synergies. By integrating standardized tasks and physiologically realistic models into the open-source framework of MyoSuite, MyoChallenge'25 serves as a reproducible and reusable testbed to accelerate interdisciplinary research across machine learning, biomechanics, sports science, and neuroscience. Project page: https://www.myosuite.org//myochallenge/myochallenge-2025.

Cheryl Wang, Chun Kwang Tan, Balint K. Hodossy +21

1McGill University, Canada · 2National University of Singapore, Singapore · Imperial College London, UK +10

Athleticism Biomechanics Mujoco General Intelligence

May 14, 2026cs.AI

Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems

LLM-based autonomous agents have demonstrated strong capabilities in reasoning, planning, and tool use, yet remain limited when tasks require sustained coordination across roles, tools, and environments. Multi-agent systems address this through structured collaboration among specialized agents, but tighter coordination also amplifies a less explored risk: errors can propagate across agents and interaction rounds, producing failures that are difficult to diagnose and rarely translate into structural self-improvement. Existing surveys cover individual agent capabilities, multi-agent collaboration, or agent self-evolution separately, leaving the causal dependencies among them unexamined. This survey provides a unified review organized around four causally linked stages, which we term the LIFE progression: Lay the capability foundation, Integrate agents through collaboration, Find faults through attribution, and Evolve through autonomous self-improvement. For each stage, we provide systematic taxonomies and formally characterize the dependencies between adjacent stages, revealing how each stage both depends on and constrains the next. Beyond synthesizing existing work, we identify open challenges at stage boundaries and propose a cross-stage research agenda for closed-loop multi-agent systems capable of continuously diagnosing failures, reorganizing structures, and refining agent behaviors, extending current coordination frameworks toward more self-organizing forms of collective intelligence. By bridging these previously fragmented research threads, this survey aims to offer both a systematic reference and a conceptual roadmap toward autonomous, self-improving multi-agent intelligence.

Shihao Qi, Jie Ma, Rui Xing +15

MOE KLINNS Lab · School of Cyber Science and Engineering, Xi’an Jiaotong University · School of Software Engineering, Xi’an Jiaotong University +6

Model-Based Multi-Agent Systems Autonomous Agents Self-Evolving Agents Collaboration Self-Evolution General Intelligence

May 7, 2026cs.AI

Uneven Evolution of Cognition Across Generations of Generative AI Models

The pursuit of artificial general intelligence necessitates robust methods for evaluating the cognitive capabilities of models beyond narrow task performance. Here, we introduce a psychometric framework to assess the cognitive profiles of generative AI, comparing them to human norms and tracking their evolution across generations. Initial evaluation of leading multimodal models using tasks adapted from the Wechsler Adult Intelligence Scale revealed a profoundly uneven cognitive architecture: near-ceiling performance in verbal comprehension and working memory (>

98^{\text{th}}

percentile) contrasted with near-floor performance in perceptual reasoning (<

1^{\text{st}}

percentile). To track developmental trajectories beyond human-normed limits, we developed the Artificial Intelligence Quotient (AIQ) Benchmark and applied it to six generations and two model families, revealing significant but asymmetric performance gains. Notably, we uncovered a sharp dissociation between modalities; abstract quantitative reasoning matured far more rapidly when presented linguistically compared to a visually analogous format, indicating an architectural bias towards language-based symbolic manipulation. While abstract visual reasoning improved, visual-perceptual organization remained largely stagnant. Collectively, these findings demonstrate that the cognitive abilities of generative models are evolving unevenly, suggesting that scaling and optimization approaches to AGI development alone may be insufficient to overcome fundamental architectural limitations in achieving balanced, human-like general intelligence.

Isaac Galatzer-Levy, Daniel McDuff, Xin Liu +1

1Google DeepMind · 2Google Research · University of Washington

Generative Artificial Intelligence Cognitive Science General Intelligence

May 5, 2026cs.RO

From Ontology Conformance to Admissible Reconfiguration: A RoSO/SMGI Adequacy Argument for Robotic Service Governance

The Robotic Service Ontology (RoSO) gives service robotics a typed semantic vocabulary for services, functions, interactions, and deployment-sensitive constraints. Its public revision trail makes visible a harder question than ontology conformance alone can settle: once a service is rebound, recomposed, repaired, or redeployed, under what conditions does the resulting configuration remain an admissible realization of the same protected service? This article argues that the Structural Model of General Intelligence (SMGI) is relevant exactly at that level \citep{osmani2026smgi}. SMGI adds not only a structural interface

θ

, but an induced behavioral semantics

T_θ

and a governance discipline for norm-respecting change. We show that RoSO can be embedded into SMGI as a typed semantic layer, so that service descriptions become dynamically governable rather than merely well formed. This yields a RoSO-to-SMGI adequacy theorem, identity-preserving reconfiguration criteria, and compositional conditions under which locally acceptable updates remain globally admissible. The resulting claim is not that SMGI replaces RoSO, but that it provides a formal account of what admissible runtime change requires once service semantics must survive revision.

Aomar Osmani

Reconfiguration Ontology Robot Systems General Intelligence

May 4, 2026cs.AI

Intervention Complexity as a Canonical Reward and a Measure of Intelligence

The Legg--Hutter universal intelligence measure provides a rigorous scalar assessment of general intelligence as expected reward across all computable environments, weighted by simplicity. However, the measure presupposes an externally specified reward function, raising the question of whether the reward primitive is inherently arbitrary or whether a canonical choice exists. We propose a new measure, called intervention complexity, that has five natural properties: environment-derivedness, universality, minimality, sensitivity, and achievement preference. Given a resource function rho encoding an inductive bias (such as program length, execution time, or energy), rho-intervention complexity is a universal reward. The result yields a family of canonical rewards indexed by resource bias, providing a principled completion of the Legg--Hutter framework that does not require external normative input. We further propose a two-dimensional characterisation of intelligence: agent competence (how well the agent performs relative to the oracle optimum) and learning efficiency (how quickly this competence improves with experience). A separation theorem establishes that the choice of resource bias determines the computability of the resulting measure: action-count IC is computable in polynomial time, while program-length IC without oracle access is uncomputable, with the gap between oracle and bare IC precisely quantifying the information-theoretic content of learning. We discuss implications for superintelligence and for pre-training universal agents.

Brendan McCane

School of Computing University of Otago Dunedin, New Zealand

General Intelligence Intelligence Tractability Rationality Reward Signal Measures+1

Apr 27, 2026cs.LG

A Limit Theory of Foundation Models: A Mathematical Approach to Understanding Emergent Intelligence and Scaling Laws

Emergent intelligence have played a major role in the modern AI development. While existing studies primarily rely on empirical observations to characterize this phenomenon, a rigorous theoretical framework remains underexplored. This study attempts to develop a mathematical approach to formalize emergent intelligence from the perspective of limit theory. Specifically, we introduce a performance function E(N, P, K), dependent on data size N, model size P and training steps K, to quantify intelligence behavior. We posit that intelligence emerges as a transition from finite to effectively infinite knowledge, and thus recast emergent intelligence as existence of the limit

\lim_{N,P,K \to \infty} \mathcal{E}(N,P,K)

, with emergent abilities corresponding to the limiting behavior. This limit theory helps reveal that emergent intelligence originates from the existence of a parameter-limit architecture (referred to as the limit architecture), and that emergent intelligence rationally corresponds to the learning behavior of this limit system. By introducing tools from nonlinear Lipschitz operator theory, we prove that the necessary and sufficient conditions for existence of the limit architecture. Furthermore, we derive the scaling law of foundation models by leveraging tools of Lipschitz operator and covering number. Theoretical results show that: 1) emergent intelligence is governed by three key factors-training steps, data size and the model architecture, where the properties of basic blocks play a crucial role in constructing foundation models; 2) the critical condition Lip(T)=1 for emergent intelligence provides theoretical support for existing findings. 3) emergent intelligence is determined by an infinite-dimensional system, yet can be effectively realized in practice through a finite-dimensional architecture. Our empirical results corroborate these theoretical findings.

Jun Shu, Junxiong Jia, Deyu Meng +1

School of Mathematics and Statistics, Xi’an Jiaotong University.

General Intelligence Emergence Wireless Foundation Models Fundamental Limits Foundation Model Mathematics

Apr 21, 2026cs.IT

Watts-per-Intelligence Part II: Algorithmic Catalysis

We develop a thermodynamic theory of algorithmic catalysis within the watts per intelligence framework, identifying reusable computational structures that reduce irreversible operations for a task class while satisfying bounded restoration and structural selectivity constraints. We prove that any class specific speed-up is upper-bounded by the algorithmic mutual information between the substrate and the class descriptor, and that encoding this information incurs a minimum thermodynamic cost via Landauer erasure. Combining these results yields a coupling theorem that lower-bounds the deployment horizon required for an algorithmic catalyst to be energetically favourable. The framework is illustrated on an affine SAT class and situates contemporary learned systems within an information thermodynamic constraint on intelligent computation.

Elija Perrier

Centre for Quantum Software and Information, University of Technology Sydney, Australia.

Thermodynamics Information-Theoretic Limits Tractability Heterogeneous Catalysis Irreversibility General Intelligence+2

Apr 21, 2026cs.CL

Are Large Language Models Economically Viable for Industry Deployment?

Generative AI-powered by Large Language Models (LLMs)-is increasingly deployed in industry across healthcare decision support, financial analytics, enterprise retrieval, and conversational automation, where reliability, efficiency, and cost control are critical. In such settings, models must satisfy strict constraints on energy, latency, and hardware utilization-not accuracy alone. Yet prevailing evaluation pipelines remain accuracy-centric, creating a Deployment-Evaluation Gap-the absence of operational and economic criteria in model assessment. To address this gap, we present EDGE-EVAL-a industry-oriented benchmarking framework that evaluates LLMs across their full lifecycle on legacy NVIDIA Tesla T4 GPUs. Benchmarking LLaMA and Qwen variants across three industrial tasks, we introduce five deployment metrics-Economic Break-Even (Nbreak), Intelligence-Per-Watt (IPW ), System Density (\r{ho}sys), Cold-Start Tax (Ctax), and Quantization Fidelity (Qret)-capturing profitability, energy efficiency, hardware scaling, serverless feasibility, and compression safety. Our results reveal a clear efficiency frontier-models in the <2B parameter class dominate larger baselines across economic and ecological dimensions. LLaMA-3.2-1B (INT4) achieves ROI break-even in 14 requests (median), delivers 3x higher energy-normalized intelligence than 7B models, and exceeds 6,900 tokens/s/GB under 4-bit quantization. We further uncover an efficiency anomaly-while QLoRA reduces memory footprint, it increases adaptation energy by up to 7x for small models-challenging prevailing assumptions about quantization-aware training in edge deployment.

Abdullah Mohammad, Sushant Kumar Ray, Pushkar Arora +5

DSEU-Okhla, New Delhi, India · University of Delhi, New Delhi, India · 6, 8Macquarie University, Sydney, Australia +1

Rate Scaling Quantization-Aware Training General Intelligence

Jul 25, 2025cs.LG

The Ratchet Effect in Silico: How Interaction Drives Cumulative Intelligence in Large Language Models

Human intelligence scales through cumulative cultural evolution (CCE), a ratchet process in which innovations are retained against entropic drift. Large language model training, by contrast, still depends primarily on static corpora and parameter growth, leaving little room for endogenous accumulation through interaction. We present POLIS (Population Orchestrated Learning and Inference Society), a framework in which heterogeneous agents generate solutions, verify one another's outputs, retain validated artifacts in shared cultural memory, and internalize them through parameter updates. On mathematical reasoning benchmarks, populations of 1--4B-parameter models achieved average gains of 8.8--18.9 points over base models and narrowed the gap to 70B+ monoliths. Mechanistic ablations identify peer verification as the main ratchet operator and show that internalization sustains accumulation across rounds, providing computational evidence that epistemic vigilance organizes durable knowledge growth. These results position structured social interaction as a scaling lever orthogonal to parameter count.

Ren Zhuang

School of Information Science and Technology, Hangzhou Normal University

General Intelligence

May 14, 2025cs.LG

Disassociating performance from compositional feature learning

Out-of-distribution (OOD) generalisation through composition requires a system to discover invariant properties from input-output associations and transfer them to novel inputs and unseen tasks. We argue that confirming compositional learning requires more than OOD evaluation alone: one must also verify that the learned features are genuinely compositional and that the system encodes their compositional rules. We demonstrate this through two tasks with clearly defined OOD metrics, generated via composable high-level abstractions, on which three standard architectures (MLP, CNN, Transformer) and an object-centric, slot-based architecture fail to generalise OOD. We pair these tasks with two novel attention-based architectures featuring an interpretable final hidden layer designed to expose whether compositional representations emerge. One architecture carries an engineered inductive bias that enables near-perfect OOD performance on one task. Our results show that even with appropriate biases and near-perfect OOD accuracy, a model can fail to learn the compositional feature structures necessary for systematic generalisation. The interpretable layer reveals that successful OOD performance is driven by task-specific biases rather than the discovery of reusable compositional primitives. These findings indicate that OOD benchmarks alone are insufficient for evaluating compositionality in neural networks.

George Dimitriadis, Spyridon Samothrakis

Computer Science and Electronic Engineering Department of the University of Essex

Compositional Generalization Out-Of-Distribution Feature Learning Convolutional Neural Networks General Intelligence