arXiv subjects

Rui Ponte Costa

Publications and source records attributed to Rui Ponte Costa.

16 recordsLinked to original sources

arXiv2026

CivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI

We present CivBench, an open-source benchmark for evaluating language model agents in long-horizon, tool-mediated environments through the Model Context Protocol (MCP). A single episode spans 300+ turns and produces thousands of tool calls over a large action space, requiring sustained planning, state monitoring, and execution under partial observability. The environment exposes 76 MCP tools and a narration layer that converts visual game state into structured text. We use CivBench to characterise agent behaviour across four model families in 23 admissible runs. The sample is a pilot, not a model ranking: aggregate outcomes do not reliably discriminate models at this scale. Instead, we introduce two interface-level metrics that the environment makes measurable: Proactive Monitoring Rate (PMR), capturing whether agents actively query latent strategic state, and RAG@10, capturing whether commitments stated in structured planning reflections are executed within ten subsequent turns. Across runs we observe two consistent patterns under a shared playbook protocol. Agents under-monitor strategically relevant state that is available but requires explicit querying: despite playbook guidance to query victory progress every 20 turns, agents do so only every 30 to 75 turns, and in 7 of 20 detectable defeats they failed to query within the 20 turn warning window before game end. Agents also frequently fail to execute near-term commitments stated in their own planning reflections (RAG@10 between 48.2% and 65.8% across models). Both patterns arise despite tool access and explicit guidance, and we interpret them as deviations under instruction rather than absences of capability. We release the environment, scenarios, logs, metrics, and analysis pipeline at https://github.com/lmwilki/civ6-mcp

cs.AI↗

arXiv2026

Task-guided cross-subject latent alignment: a multi-encoder-decoder VAE

Aligning neural activity across subjects offers the promise of discovering shared computational principles and generalizable decoders. However, traditional alignment methods require shared stimuli across subjects, a constraint that limits applicability to naturalistic paradigms with limited or non-overlapping data. We introduce a Multi-Encoder-Decoder Variational Autoencoder (MED-VAE) that achieves cross-subject alignment without shared stimuli by anchoring representations to a common scaffold provided by a pretrained ANN. Using the Natural Scenes Dataset, we show that MED-VAE creates common latent spaces with superior semantic organisation, achieving higher cross-subject alignment than common methods while maintaining robust generalisation to held-out stimuli where traditional methods degrade. Reconstructing from these common spaces back to each subject's original neural space, MED-VAE preserves equal stimulus-driven signal in its cross-subject latent space. Finally, we show that this superior alignment directly enables cross-subject neural prediction, as demonstrated via cross-subject image decoding. In summary, we introduce a framework to identify generalisable common subspaces for cross-subject predictions and downstream tasks, demonstrated here for visual cortex responses to static images.

q-bio.NC↗

arXiv2026

Reason to Play: Behavioral and Brain Alignment Between Frontier LRMs and Human Game Learners

Humans rapidly learn abstract knowledge when encountering novel environments and flexibly deploy this knowledge to guide efficient and intelligent action. Can modern AI systems learn and plan in a similar way? We study this question using a dataset of complex human gameplay with concurrent fMRI recordings, in which participants learn novel video games that require rule discovery, hypothesis revision, and multi-step planning. We jointly evaluate models by their ability to play the games, match human learning behavior, and predict brain activity during the same task, comparing a suite of frontier Large Reasoning Models (LRMs) against model-free and model-based deep reinforcement learning agents and a Bayesian theory-based agent. We find that frontier LRMs most closely match human behavioral patterns during game discovery and predict brain activity an order of magnitude better than both reinforcement learning alternatives across cortical and subcortical regions, with effects robust to permutation controls. Through targeted manipulations, we further show that brain alignment reflects the model's in-context representation of the game state rather than its downstream planning or reasoning. Our results establish LRMs as compelling computational accounts of human learning and decision making in complex, naturalistic environments. Project page with interactive replays: https://botcs.github.io/reason-to-play/

cs.AI↗

arXiv2026

Neural mechanisms of predictive processing: a collaborative community experiment through the OpenScope program

This review synthesizes advances in predictive processing within the sensory cortex. Predictive processing theorizes that the brain continuously predicts sensory inputs, refining neuronal responses by highlighting prediction errors. We identify key computational primitives, such as stimulus adaptation, dendritic computation, excitatory/inhibitory balance and hierarchical processing, as central to this framework. Our review highlights convergences, such as top-down inputs and inhibitory interneurons shaping mismatch signals, and divergences, including species-specific hierarchies and modality-dependent layer roles. To address these conflicts, we propose experiments in mice and primates using in-vivo two-photon imaging and electrophysiological recordings to test whether temporal, motor, and omission mismatch stimuli engage shared or distinct mechanisms. The resulting dataset, collected and shared via the OpenScope program, will enable model validation and community analysis, fostering iterative refinement and refutability to decode the neural circuits of predictive processing.

q-bio.NC↗

arXiv2025

Brain-Like Processing Pathways Form in Models With Heterogeneous Experts

The brain is made up of a vast set of heterogeneous regions that dynamically organize into pathways as a function of task demands. Examples of such pathways can be found in the interactions between cortical and subcortical networks during learning, or in sub-networks specializing for task characteristics such as difficulty or modality. Despite the large role these pathways play in cognition, the mechanisms through which brain regions organize into pathways remain unclear. In this work, we use an extension of the Heterogeneous Mixture-of-Experts architecture to show that heterogeneous regions do not form processing pathways by themselves, implying that the brain likely implements specific constraints which result in the reliable formation of pathways. We identify three biologically relevant inductive biases that encourage pathway formation: a routing cost imposed on the use of more complex regions, a scaling factor that reduces this cost when task performance is low, and randomized expert dropout. When comparing our resulting \textit{Mixture-of-Pathways} model with the brain, we observe that the artificial pathways in our model match how the brain uses cortical and subcortical systems to learn and solve tasks of varying difficulty. In summary, we introduce a novel framework for investigating how the brain forms task-specific pathways through inductive biases, and the effects these biases have on the behavior of Mixture-of-Experts models.

q-bio.NC↗

arXiv2024

Dynamical similarity analysis can identify compositional dynamics developing in RNNs

Methods for analyzing representations in neural systems have become a popular tool in both neuroscience and mechanistic interpretability. Having measures to compare how similar activations of neurons are across conditions, architectures, and species, gives us a scalable way of learning how information is transformed within different neural networks. In contrast to this trend, recent investigations have revealed how some metrics can respond to spurious signals and hence give misleading results. To identify the most reliable metric and understand how measures could be improved, it is going to be important to identify specific test cases which can serve as benchmarks. Here we propose that the phenomena of compositional learning in recurrent neural networks (RNNs) allows us to build a test case for dynamical representation alignment metrics. By implementing this case, we show it enables us to test whether metrics can identify representations which gradually develop throughout learning and probe whether representations identified by metrics are relevant to computations executed by networks. By building both an attractor- and RNN-based test case, we show that the new Dynamical Similarity Analysis (DSA) is more noise robust and identifies behaviorally relevant representations more reliably than prior metrics (Procrustes, CKA). We also show how test cases can be used beyond evaluating metrics to study new architectures. Specifically, results from applying DSA to modern (Mamba) state space models, suggest that, in contrast to RNNs, these models may not exhibit changes to their recurrent dynamics due to their expressiveness. Overall, by developing test cases, we show DSA's exceptional ability to detect compositional dynamical motifs, thereby enhancing our understanding of how computations unfold in RNNs.

cs.LG↗

arXiv2024

Lost in Latent Space: Disentangled Models and the Challenge of Combinatorial Generalisation

Recent research has shown that generative models with highly disentangled representations fail to generalise to unseen combination of generative factor values. These findings contradict earlier research which showed improved performance in out-of-training distribution settings when compared to entangled representations. Additionally, it is not clear if the reported failures are due to (a) encoders failing to map novel combinations to the proper regions of the latent space or (b) novel combinations being mapped correctly but the decoder/downstream process is unable to render the correct output for the unseen combinations. We investigate these alternatives by testing several models on a range of datasets and training settings. We find that (i) when models fail, their encoders also fail to map unseen combinations to correct regions of the latent space and (ii) when models succeed, it is either because the test conditions do not exclude enough examples, or because excluded generative factors determine independent parts of the output image. Based on these results, we argue that to generalise properly, models not only need to capture factors of variation, but also understand how to invert the generative process that was used to generate the data.

cs.LG↗

arXiv2024

BP(λ): Online Learning via Synthetic Gradients

Training recurrent neural networks typically relies on backpropagation through time (BPTT). BPTT depends on forward and backward passes to be completed, rendering the network locked to these computations before loss gradients are available. Recently, Jaderberg et al. proposed synthetic gradients to alleviate the need for full BPTT. In their implementation synthetic gradients are learned through a mixture of backpropagated gradients and bootstrapped synthetic gradients, analogous to the temporal difference (TD) algorithm in Reinforcement Learning (RL). However, as in TD learning, heavy use of bootstrapping can result in bias which leads to poor synthetic gradient estimates. Inspired by the accumulate $\mathrm{TD}(λ)$ in RL, we propose a fully online method for learning synthetic gradients which avoids the use of BPTT altogether: accumulate $BP(λ)$. As in accumulate $\mathrm{TD}(λ)$, we show analytically that accumulate $\mathrm{BP}(λ)$ can control the level of bias by using a mixture of temporal difference errors and recursively defined eligibility traces. We next demonstrate empirically that our model outperforms the original implementation for learning synthetic gradients in a variety of tasks, and is particularly suited for capturing longer timescales. Finally, building on recent work we reflect on accumulate $\mathrm{BP}(λ)$ as a principle for learning in biological circuits. In summary, inspired by RL principles we introduce an algorithm capable of bias-free online learning via synthetic gradients.

cs.LG↗

arXiv2022

Single-phase deep learning in cortico-cortical networks

The error-backpropagation (backprop) algorithm remains the most common solution to the credit assignment problem in artificial neural networks. In neuroscience, it is unclear whether the brain could adopt a similar strategy to correctly modify its synapses. Recent models have attempted to bridge this gap while being consistent with a range of experimental observations. However, these models are either unable to effectively backpropagate error signals across multiple layers or require a multi-phase learning process, neither of which are reminiscent of learning in the brain. Here, we introduce a new model, Bursting Cortico-Cortical Networks (BurstCCN), which solves these issues by integrating known properties of cortical networks namely bursting activity, short-term plasticity (STP) and dendrite-targeting interneurons. BurstCCN relies on burst multiplexing via connection-type-specific STP to propagate backprop-like error signals within deep cortical networks. These error signals are encoded at distal dendrites and induce burst-dependent plasticity as a result of excitatory-inhibitory top-down inputs. First, we demonstrate that our model can effectively backpropagate errors through multiple layers using a single-phase learning process. Next, we show both empirically and analytically that learning in our model approximates backprop-derived gradients. Finally, we demonstrate that our model is capable of learning complex image classification tasks (MNIST and CIFAR-10). Overall, our results suggest that cortical features across sub-cellular, cellular, microcircuit and systems levels jointly underlie single-phase efficient deep learning in the brain.

q-bio.NC↗

arXiv2022

Current State and Future Directions for Learning in Biological Recurrent Neural Networks: A Perspective Piece

We provide a brief review of the common assumptions about biological learning with findings from experimental neuroscience and contrast them with the efficiency of gradient-based learning in recurrent neural networks. The key issues discussed in this review include: synaptic plasticity, neural circuits, theory-experiment divide, and objective functions. We conclude with recommendations for both theoretical and experimental neuroscientists when designing new studies that could help bring clarity to these issues.

q-bio.NC↗

arXiv2021

Cortico-cerebellar networks as decoupling neural interfaces

The brain solves the credit assignment problem remarkably well. For credit to be assigned across neural networks they must, in principle, wait for specific neural computations to finish. How the brain deals with this inherent locking problem has remained unclear. Deep learning methods suffer from similar locking constraints both on the forward and feedback phase. Recently, decoupled neural interfaces (DNIs) were introduced as a solution to the forward and feedback locking problems in deep networks. Here we propose that a specialised brain region, the cerebellum, helps the cerebral cortex solve similar locking problems akin to DNIs. To demonstrate the potential of this framework we introduce a systems-level model in which a recurrent cortical network receives online temporal feedback predictions from a cerebellar module. We test this cortico-cerebellar recurrent neural network (ccRNN) model on a number of sensorimotor (line and digit drawing) and cognitive tasks (pattern recognition and caption generation) that have been shown to be cerebellar-dependent. In all tasks, we observe that ccRNNs facilitates learning while reducing ataxia-like behaviours, consistent with classical experimental observations. Moreover, our model also explains recent behavioural and neuronal observations while making several testable predictions across multiple levels. Overall, our work offers a novel perspective on the cerebellum as a brain-wide decoupling machine for efficient credit assignment and opens a new avenue between deep learning and neuroscience.

q-bio.NC↗

arXiv2021

Learning offline: memory replay in biological and artificial reinforcement learning

Learning to act in an environment to maximise rewards is among the brain's key functions. This process has often been conceptualised within the framework of reinforcement learning, which has also gained prominence in machine learning and artificial intelligence (AI) as a way to optimise decision-making. A common aspect of both biological and machine reinforcement learning is the reactivation of previously experienced episodes, referred to as replay. Replay is important for memory consolidation in biological neural networks, and is key to stabilising learning in deep neural networks. Here, we review recent developments concerning the functional roles of replay in the fields of neuroscience and AI. Complementary progress suggests how replay might support learning processes, including generalisation and continual learning, affording opportunities to transfer knowledge across the two fields to advance the understanding of biological and artificial learning and memory.

cs.LG↗

arXiv2018

Dendritic cortical microcircuits approximate the backpropagation algorithm

Deep learning has seen remarkable developments over the last years, many of them inspired by neuroscience. However, the main learning mechanism behind these advances - error backpropagation - appears to be at odds with neurobiology. Here, we introduce a multilayer neuronal network model with simplified dendritic compartments in which error-driven synaptic plasticity adapts the network towards a global desired output. In contrast to previous work our model does not require separate phases and synaptic learning is driven by local dendritic prediction errors continuously in time. Such errors originate at apical dendrites and occur due to a mismatch between predictive input from lateral interneurons and activity from actual top-down feedback. Through the use of simple dendritic compartments and different cell-types our model can represent both error and normal activity within a pyramidal neuron. We demonstrate the learning capabilities of the model in regression and classification tasks, and show analytically that it approximates the error backpropagation algorithm. Moreover, our framework is consistent with recent observations of learning between brain areas and the architecture of cortical microcircuits. Overall, we introduce a novel view of learning on dendritic cortical circuits and on how the brain may solve the long-standing synaptic credit assignment problem.

q-bio.NC↗

arXiv2018

Cortical microcircuits as gated-recurrent neural networks

Cortical circuits exhibit intricate recurrent architectures that are remarkably similar across different brain areas. Such stereotyped structure suggests the existence of common computational principles. However, such principles have remained largely elusive. Inspired by gated-memory networks, namely long short-term memory networks (LSTMs), we introduce a recurrent neural network in which information is gated through inhibitory cells that are subtractive (subLSTM). We propose a natural mapping of subLSTMs onto known canonical excitatory-inhibitory cortical microcircuits. Our empirical evaluation across sequential image classification and language modelling tasks shows that subLSTM units can achieve similar performance to LSTM units. These results suggest that cortical circuits can be optimised to solve complex contextual problems and proposes a novel view on their computational function. Overall our work provides a step towards unifying recurrent networks as used in machine learning with their biological counterparts.

q-bio.NC↗

arXiv2017

Dendritic error backpropagation in deep cortical microcircuits

Animal behaviour depends on learning to associate sensory stimuli with the desired motor command. Understanding how the brain orchestrates the necessary synaptic modifications across different brain areas has remained a longstanding puzzle. Here, we introduce a multi-area neuronal network model in which synaptic plasticity continuously adapts the network towards a global desired output. In this model synaptic learning is driven by a local dendritic prediction error that arises from a failure to predict the top-down input given the bottom-up activities. Such errors occur at apical dendrites of pyramidal neurons where both long-range excitatory feedback and local inhibitory predictions are integrated. When local inhibition fails to match excitatory feedback an error occurs which triggers plasticity at bottom-up synapses at basal dendrites of the same pyramidal neurons. We demonstrate the learning capabilities of the model in a number of tasks and show that it approximates the classical error backpropagation algorithm. Finally, complementing this cortical circuit with a disinhibitory mechanism enables attention-like stimulus denoising and generation. Our framework makes several experimental predictions on the function of dendritic integration and cortical microcircuits, is consistent with recent observations of cross-area learning, and suggests a biological implementation of deep learning.

q-bio.NC↗

arXiv2015

Computational model of axon guidance

Axon guidance (AG) towards their target during embryogenesis or after injury is an important issue in the development of neuronal networks. During their growth, axons often face complex decisions that are difficult to understand when observing just a small part of the problem. In this work we propose a computational model of AG based on activity-independent mechanisms that takes into account the most important aspects of AG. The model includes the main elements (neurons, with soma, axon and growth cone; glial cells acting as guideposts) and mechanisms (attraction/repulsion guidance cues, growth cone adaptation, tissue-gradient intersections, axonal transport, changes in the growth cone complexity and a range of responses for each receptor). The growth cone guidance is defined as a function that maps the receptor activation by ligands into a repulsive or attractive force. This force is then converted into a turn- ing angle using spherical coordinates. A regulatory network between the receptors and the intracellular proteins is considered, leading to more complex and realistic behaviors. The ligand diffusion through the extracellular environment is modeled with linear or exponential functions. Concerning experimentation, it was developed the first computational model and a new theoretical model of the midline crossing of Drosophila axons that focus all the decision points. The computational model created allows describing to a great extent the behaviors that have been reported in the literature, for three different pathfinding scenarios: (i) normal, (ii) comm mutant and (iii) robo mutant. Moreover, this model suggests new hypotheses, being the most relevant the existence of an inhibitory link between the DCC receptor and the Comm protein that is Netrin-mediated or mediated by a third unknown signal.

q-bio.NC↗