Sección

Investigación

Papers y preprints de los feeds de investigación que seguimos.

6415documentos

FlowMaker: From Tasks to Cost-Efficient Generative AI Workflow Deployments

Generative AI workflows execute user tasks by composing sequences of LLM calls, where each call performs a sub-task (e.g., summarization or translation), forming a workflow. Executing such workflows requires decisions over workflow structure, model assignments, and deployment configurations, which jointly determine latency, cost, and accuracy under dynamic workloads and resource constraints. Existing systems optimize these decisions in isolation or fix them early, leading to suboptimal cost and goodput. We make two key observations. First, efficient serving requires jointly exploring all combinations of workflows, model choices, and deployment configurations under dynamic cluster state. Second, reuse of deployed LLMs is critical for reducing cost, but must be performed on-the-fly, as reuse depends on current load and resource availability. Together, these make selecting a workflow-variant-a combination of workflow, models, and deployment configuration-a time-critical problem. We present FlowMaker, which exposes a task-level interface and selects workflow-variants on behalf of users. To realize this, we design a constraint-guided load-aware pruning algorithm for fast, on-the-fly decisions. FlowMaker improves goodput by up to 10.14and reduces cost by up to 2.77compared to state-of-the-art baselines, including Murakkab.

arXiv AI Papershace 27 días

LLM-Based Evaluation Planning for Heterogeneous Optimization

Heterogeneous optimization problems require an optimizer to decide not only which candidate solutions to evaluate, but also which objectives and constraints should be evaluated under different costs and fidelities. Existing SOTA methods such as MFE-NSGA-III address this setting with manually designed selection metrics, but their behavior is largely determined by predefined heuristic rules and hyperparameters. In this work, we propose REP-HO, a reasoning-based evaluation planner that replaces the rule-based mixed-fidelity selection step with a large language model (LLM) planner. The LLM receives the same primitive optimization-state information as the heuristic planner, such as surrogate predictions, uncertainties, evaluation costs, and budget status. We first show that REP-HO achieves competitive performance compared to the human-designed metric-based method (MFE-NSGA-III). We then further enhance each decision with an adaptive nearest-neighbor summary, leading to better and more stable results. We evaluate REP-HO across five heterogeneous regimes covering cost imbalance, constraint difficulty, surrogate fidelity, budget level, and objective conflict. Across these regimes, one of the two variants obtains the best mean ranking score in every regime, REP-HO(Deepseek) is first or second throughout, and the planner shows adaptive allocation behavior, such as prioritizing constraint evaluations under tighter budgets and reallocating constraint evaluation budget when surrogate reliability changes. These results suggest that LLMs can serve as flexible evaluation planners for heterogeneous optimization, offering a general alternative to fixed hand-designed metrics.

arXiv AI Papershace 27 días

Learning to Program Retrievals: Composing Search Primitives via Reinforcement Learning

Retrieval-augmented language models increasingly use multi-step search to solve knowledge-intensive tasks, yet existing systems typically expose retrieval through fixed pipelines or collections of atomic tools. We introduce Retrieval Program Learning (RPL), a programmable search framework that allows a policy to compose search primitives into executable programs with local state and control flow. This enables adaptive search that can retrieve broadly, process intermediate results, and selectively construct model context without tying retrieval breadth to context consumption. However, the resulting flexibility creates a difficult exploration problem: useful programs may require several coordinated decisions, while reinforcement learning often supplies only sparse feedback. To address this challenge, we propose program mutation, a grammar-constrained and execution-verified procedure that generates local variants of suboptimal programs sampled during RL, converts them into training trajectories, and distills them back into the policy. We evaluate RPL on open-domain question answering and corpus-level reasoning tasks, comparing it with a range of retrieval and reasoning baselines. RPL consistently improves open-domain QA performance across model sizes and in- and out-of-domain benchmarks, with particularly large gains on multi-hop tasks. Notably, a 4B model trained with RPL outperforms all 8B model baselines. On corpus-level reasoning, RPL achieves the highest answer F1 and document-coverage F1 for both model sizes while substantially reducing context consumption and retrieval turns. Our results show that programmable search expands the retrieval strategies that agents can learn, while program mutation provides an effective mechanism for exploring useful program structures beyond direct on-policy sampling.

arXiv AI Papershace 27 días

MisleadQA: Diagnosing LLM Failures under Misleading Context

Large language models (LLMs) are widely used to answer questions from retrieved or user-provided context. However, provided context can be factually true yet out-of-scope, describing a different entity, time, or location from the one the question targets, and still lead models to a wrong answer. Prior work has mainly studied factually false or irrelevant context. It remains unclear whether such out-of-scope context misleads models as much as false context, and whether adding gold context prevents models from being misled by either. We introduce **MisleadQA**, a diagnostic dataset of multiple-choice questions with an abstention option. Each question pairs gold context (G) with true but out-of-scope context (S) and false but in-scope context (F) supporting the same wrong answer. We evaluate six open-weight LLMs. On questions they answer correctly without context, providing S alone leads them to switch to this wrong answer in 29.3% of cases, and providing F alone does so in 75.4%. Adding G nearly removes the effect of S, but F still misleads models in 21.0% of cases, especially when F comes first. A context-faithful instruction reduces these errors mainly through abstention and lowers accuracy even with G. These findings suggest that evaluations should check whether context applies to the question, not only whether it is true, and should report correct, misled, and abstention rates together. Data and code are available at [https://anonymous.4open.science/r/MisleadQA](https://anonymous.4open.science/r/MisleadQA).

arXiv AI Papershace 27 días

An Impossibility Result for ETF Target Geometry, and an Equinorm Remedy for Imbalanced Analytic Continual Learning

Analytic continual learning (ACL) methods such as ACIL and GACL fit a ridge-regression classifier head on frozen features via the Sherman-Morrison-Woodbury identity, achieving exemplar-free, exact updates. A separate line of work, Progressive Neural Collapse (ProNC), shows standard continual classifiers benefit from a progressively expanding Simplex Equiangular Tight Frame (ETF) target. It is natural to ask whether fusing the two ideas, exact analytic updates and ETF targets, would yield a better closed-form continual learner. We show this is not the case as the fusion turns out to be identical to plain one-hot ACIL. Further, Simplex ETFs are not nested across class counts, so the literal "progressively expand the ETF" construction stops yielding an ETF as new tasks arrive, and it introduces catastrophic forgetting (4that of a classic ACIL head). We therefore separate an ETF's two defining properties, equiangularity and equinormality, and apply each on its own to the classifier weights rather than the targets, where the invariance above does not hold. Equinorm post-processing of the fitted weights recovers both tail-class and overall average accuracy across the long-tailed regime from 5:1 to 100:1 imbalance (e.g. +32.0 tail-accuracy points and +16.0 average-accuracy points at 100:1 on CIFAR-100/ViT), transferring in sign across two backbones and two datasets, at a mild cost of 5.4 average-accuracy points on CIFAR-100/ViT on near-balanced streams (below 3{:}1). Equiangular geometry, by contrast, is exactly inert on the target side but actively harmful on the weight side, usually losing to plain one-hot. Hence, the generally useful part of Neural Collapse geometry in Analytic Continual Learning is equinorm post-processing of the weights, becoming more useful as class imbalance grows; and equiangularity is at best a no-op and induces catastrophic forgetting at worst.

arXiv AI Papershace 27 días

A Statistical Viewpoint on Adam, Shampoo and Muon

We provide new statistical insights into designing stochastic optimization methods. By modeling the gradient via a normal distribution, we argue that the stochastic gradient should be whitened using its covariance. We give an online method for estimating the mean and variance of the gradients based on regularized likelihood or, equivalently, through a maximum a posteriori estimate. We then show how to use structured approximations to the covariance within this same framework, which includes diagonal and Kronecker-factored approximations. The diagonal approximation results in a method that is very closely related to Adam and performs as well in practice. The Kronecker approximation results in the new MN method, which is a variant of Shampoo and KL-Shampoo. We also recover Muon by applying this same statistical framework to the gradient direction rather than the full gradient. By combining this with a whitening step, we arrive at MN-Muon, a novel preconditioned version of Muon. Our experiments on GPT-2-type models at Chinchilla scale indicate that MND, the diagonal implementation of MN, outperforms both the Distributed Shampoo and the KL-Shampoo implementations in terms of stability, final validation loss and time taken. MND-Muon, the diagonal implementation of MN-Muon, improves on Muon in 21 of 24 paired GPT-small runs and achieves a lower best validation loss on GPT-medium, where it remains stable over the six tested learning rates. However, we found that NorMuon was comparable to MND-Muon and achieved a slightly lower validation loss on GPT-medium and at GPT-small batch 512 on FineWeb.

arXiv AI Papershace 27 días

Pattern-Driven Evaluation of LLM Code Optimization: Isolating Compiler-Transcendent Semantic Reasoning

Existing evaluations of LLM-based code optimization primarily measure end-to-end speedup, obscuring whether a model actually performs the intended optimization. For compiled languages, this is especially problematic: observed gains may reflect transformations already recoverable by modern optimizing compilers rather than optimization behavior attributable to the model itself. We present PatternBench, a benchmark for studying compiler-transcendent optimization, i.e., performance improvements that remain after aggressive compiler optimization. PatternBench targets residual optimization opportunities across seven classes of transformations and pairs runtime evaluation with an AST-based optimization faithfulness analysis that verifies whether the intended optimization is realized in the generated program. Experiments with frontier, open-weight, and fine-tuned models show that runtime speedup alone provides an incomplete account of optimization capability. Optimization faithfulness is strongly associated with realized speedup, and fine-tuning improves both faithfulness and optimization effectiveness. These results suggest that evaluation of LLM-based code optimization should measure not only performance outcomes, but also whether the target transformation was successfully executed.

arXiv AI Papershace 27 días

Recurrent Temporal Restricted Boltzmann Machines as Unsupervised Encoders for Biomechanical Movement Sequences

Biomechanical movement recordings are continuous, high-dimensional time series, and analyzing them without manually labeling them requires representations that capture how movements evolve over time. Most unsupervised representation-learning pipelines, however, treat each observation frame independently and discard this temporal structure, while energy-based models that could capture it have not extensively been adapted to biomechanical signals. So, this paper implements the Recurrent Temporal Restricted Boltzmann Machine (RTRBM), a recurrent energy-based model, into an unsupervised encoder that maps windows of movement data to fixed-length embeddings, and tests what its recurrent structure contributes. We adapt the model to continuous-valued signals, stack it into a deep architecture, and integrate it into the SIT-FUSE segmentation pipeline. We evaluate the embeddings on simulated musculoskeletal reaching and on two real gait datasets, using clustering, reconstruction, and walking-speed classification of unseen subjects, and compare them against non-recurrent and non-probabilistic baselines, including a control that removes the recurrent connection. Clustering the embeddings recovers movement structure tied to progress toward the target without any labels, which also transfers to unseen episodes. On gait data, the embeddings outperform PCA and autoencoder baselines under a nonlinear probe. However, removing the recurrent connection does not yield a measurable loss on the reaching task, and simple per-channel summary statistics classify walking speed at least as well as the embeddings. The model is therefore a working, verified encoder for SIT-FUSE, while the evidence for a benefit of recurrence is mixed, and the learned embeddings did not outperform simple summary statistics on gait.

arXiv AI Papershace 27 días

Compose the Horizon: Parameter-Shared Blockwise Forecasting under a Sequential-Compute Trade-off

Most long-horizon forecasters emit the complete future in one pass. We ask whether a compact operator can instead be reused to emit contiguous future blocks, trading stored parameters for sequential computation. Recursive Functional Decomposition (RFD) factorizes the horizon mapping into three parameter-shared block predictions. The blocks occupy disjoint future intervals and are concatenated, not added as trend, seasonal, or residual components, and each emitted block joins the rolling context that conditions the next application. In controlled three-seed experiments, removing forward feedback hurts all four evaluated datasets while stopping gradients through it changes little, so the useful signal is the evolving forecast state itself; reapplying the shared operator helps consistently, but by less than widening it. The model uses 0.08--0.46M parameters, yet its sequential channel-wise execution is slower and more memory-intensive than an iterative baseline at high channel count. In a frozen long-context evaluation against ten strong baseline families, RFD records lower test error in 23 of 24 cells; the comparison is cross-protocol, with RFD using 512/720-step context and the baselines using 96.

arXiv AI Papershace 27 días

Teaching Code Agents to Ask Without Leaking Private Code

Local coding agents can extend their reach by consulting a stronger cloud model. Such consultations, however, often expose the repository's private identifiers, file paths, and source code. Host-side masking hides recognized identifiers but leaves the surrounding code and the agent's phrasing unchanged, while training for less disclosure risks suppressing consultation or producing questions too vague to answer. We propose utility-verified abstraction (UVA), which teaches the agent to describe private entities by their role and type while retaining the technical details an expert needs. From solved repair trajectories, we rewrite each question into this form and keep the rewrite only if it discloses fewer private entities and the repair, replayed from the same execution state with the repair trajectories. Across two benchmarks, the trained agent consults more often than before training. On repository-level issue repair, it solves 37.6% of issues, against 25.3% for the same model working alone, a gain from the training as a whole rather than from consultation alone. Its questions disclose 3.7-fold fewer private entities and 1.4-fold less verbatim code than the untrained agent's questions to the same expert.

arXiv AI Papershace 27 días

Pair-Aware Optimization: Coordinating Exploration and Refinement for Jailbreaking LLM Agents

Large Language Model (LLM) agents are vulnerable to adversarial inputs that induce attacker-specified malicious behaviors, commonly referred to as jailbreaking. Existing optimization-based jailbreak attacks primarily employ first-order (FO) methods that leverage gradient information or zeroth-order (ZO) methods that rely on function-value feedback. However, their complementarity and optimization ordering remain underexplored. We systematically investigate four strategies: pure ZO, pure FO, ZO->FO, and FO->ZO, and develop a ZO-FO framework that explores adversarial prefixes through ZO optimization and refines their corresponding suffixes through FO optimization. To coordinate the two processes, we introduce Pair-aware optimization, which retains multiple prefix candidates, conditionally refines their suffixes and selects among the resulting prefix-suffix pairs. We further investigate agent jailbreaking from a more general stochastic-generation perspective, where the same adversarial input can induce diverse reasoning trajectories and actions that a single greedy output cannot capture. Accordingly, we adopt consistent stochastic decoding during both optimization and evaluation. Experiments across malicious-instruction and malicious-environment benchmarks demonstrate that hybrid optimization improves attack effectiveness over single-optimizer methods, while optimization order substantially influences performance.

arXiv AI Papershace 27 días

Efficiency Measured in English: Tokeniser Coverage Bounds Small Language Models on Indic Scripts

Small Language Models with quantisation and parameter-efficient adaptation are widely offered as the route to multilingual AI under compute constraints, and their efficiency is almost always reported as a single memory figure. We show that this figure is measured in English and does not transfer. Across a 131k-sentence corpus spanning eleven Indic scripts, TinyLlama-1.1B's tokeniser emits 1.34 subword tokens per Latin-script word and 22.60 per Kannada word. This is not inefficiency; it is absence. Its vocabulary contains 0% of Odia's codepoints, 1% of Telugu's and 2% of Kannada's, and for five of eleven scripts the measured fertility sits at the UTF-8 byte-fallback ceiling, on Odia at 99.6% of it, with 93.6% of emitted tokens being raw bytes. Because SentencePiece byte fallback never raises an unknown-token marker, this failure is entirely silent: TinyLlama's UNK rate is 0.0% on every script, including the one it reads as bytes. We further show that low fertility can indicate the opposite of efficiency: mBERT posts its best score anywhere (1.10 tokens/word, on Odia) while discarding 87.9% of the text as UNK. MuRIL, an Indic-vocabulary encoder with a fifth of TinyLlama's parameters, reads every script at 1.23-2.26 tokens/word with zero UNK and zero byte fallback. The binding constraint is the vocabulary, not the parameter count. The consequence is concrete: on a 2048-token context window, the same model gives an English user 1,528 words of usable context and a Kannada user 91.

arXiv AI Papershace 27 días

First-Order LoRA Training with Phone NPUs

On-device fine-tuning lets a large language model (LLM) learn from its user's private data without uploading it. Low-rank adaptation (LoRA) reduces the trainable parameters, but each first-order training step still multiplies by the frozen base-model weights during the forward pass, activation recomputation, and input-gradient computation. A phone's neural processing unit (NPU) already holds these weights for inference; using it for training also requires computing input gradients, which its inference interface does not support. We present a system that runs all three frozen-weight products on the NPU while keeping the training graph, adapters, and optimizer on the CPU. Its input-gradient kernels reuse the resident weight tiles and the forward dequantizer, avoiding a transposed weight copy and ensuring forward and backward use the same effective weights. To preserve usable gradients, the system selects precision by gradient sensitivity and applies a per-row range guard for half-precision (FP16) outputs. Its runtime fuses the remaining CPU operators and overlaps NPU execution with adapter computation, while resumable execution and thermal pacing let training proceed as a background job. We evaluate it on two Qualcomm Snapdragon platforms using four LLMs from the Qwen and Llama families. Our workloads cover nightly personalization with labels supplied on the phone and the public LaMP-2 benchmark; comparisons include an optimized CPU trainer, a phone-GPU trainer, forward-only training, and GPU-trained references.

arXiv AI Papershace 27 días

Tilted Mondrian: Triage and Mitigation of Fine-grained Disparities in Conformal Prediction

Fairness in conformal prediction is often pursued through Mondrian calibration, which provides finite-sample coverage guarantees separately across groups. These guarantees, however, are coarse: substantial disparities can remain within finer strata. This coarse-to-fine fairness issue raises two questions: how severe can such disparities be, and how can they be mitigated? Aggregate disparities can depend on how groups are distributed across strata. For severity assessment, we introduce propensity standardization to examine the effect of population composition, and show how group composition can induce disagreement between aggregate and finer-stratum comparisons. For mitigation, we develop Tilted Mondrian to improve fairness compared to group-Mondrian at a finer level without additional model training. Tilted Mondrian retains groupwise coverage guarantees and mitigates coverage and prediction set size disparities within finer strata. Finally, we derive a method-agnostic bound that quantifies how much reduction in finer-stratum coverage disparity can be achieved.

arXiv AI Papershace 27 días

Ask, Don't Guess: Targeted Clarification for Speech Recognition Errors

Speech recognition in real time in far-field conversational settings still incurs significant errors. Identifying potential error spans during streaming ASR permits a recourse mechanism where the speaker can be asked to repeat the affected content under cleaner acoustic conditions. We propose , a new framework for online error localization, that identifies spans likely to benefit from this intervention. Our supervision uses clean audio to estimate how the recognizer's output might change under improved acoustic conditions. We probabilistically align noisy and clean decodes using a pair-HMM to obtain soft supervision. These soft targets train a counterfactual gain scorer by combining a suite of acoustic and language features to produce token-level scores, that are further grouped into spans for targeted recourse. An LLM uses the ASR transcript of the repetition to revise only the selected span. At a precision of 70\%, achieves the highest recall by identifying up to 52\% more erroneous tokens compared to the strongest baseline. Targeted repetition yields relative WER reductions of up to 24\% under a budget that accounts for both interruption frequency and the lengths of re-uttered spans.

arXiv AI Papershace 27 días

Medical Fine-Tuning Reshapes, Not Reduces, Patient-Facing AI Risk: A Rubric-Based, LLM-Judge Evaluation Framework

Patient-facing medical question answering with large language models (LLMs) is moving from research demonstrations to production deployments, yet evaluation remains anchored on factual correctness. Factuality is necessary but not sufficient: a response can be factually grounded and still issue a directive that, if acted on, would harm the patient. We introduce a risk-sensitive evaluation framework that scores responses by the presence and severity of six categories of risk-bearing language (treatment directives, contraindications, dosage expressions, urgency-triage cues, high-alert medication mentions, and overconfident assertions), anchored on published clinical harm taxonomies. Severity is classified by a three-judge LLM ensemble. We apply this framework to six 7-9B instruction-tuned models, three general (Mistral-7B, Phi-3.5-mini, Llama-3.1-8B) and three medically adapted (BioMistral-7B, OpenBioLLM-Llama3-8B, Med42-Llama3-8B), on 200 real patient questions from the K-QA benchmark. Two findings emerge. First, ensemble risk-bearing language is statistically independent of factual hallucination rate (pooled Spearman ρ= -0.065, n = 300, 95% CI [-0.18, +0.05]; distance correlation = 0.10, independence test p = 0.24). Second, medical fine-tuning does not reduce aggregate risk but reshapes it: continued-pretraining adaptations (BioMistral, OpenBioLLM) consistently suppress high-alert medication mentions while amplifying overconfident assertions, whereas clinical instruction-tuning (Med42) suppresses dosing only, without amplifying overconfidence. Per-category Krippendorff α is fair to good for the four linguistically anchored categories (0.53-0.71) and low for the two clinical-judgment-dependent categories (0.19, 0.31), indicating where automatic safety evaluation is and is not yet reliable. We release the rubric, judge prompts, and evaluation code.

arXiv AI Papershace 27 días

Is User Calibration Still Necessary for Continuous Myoelectric Control? A Closed-Loop Comparison of Calibration-Free Controllers

The need for user-specific calibration remains an often-cited barrier to widespread adoption of myoelectric control. Cross-user models trained on large multi-user datasets can now recognize gestures from unseen users without calibration, but they have been evaluated almost exclusively offline, leaving open whether calibration is still needed in closed-loop control. This study compared six calibration-free controllers, trained on 306 users of the EMG-EPN-612 dataset and used without any calibration data from the test participant, against three calibrated controllers in a closed-loop Fitts' law target-acquisition task with sixteen participants. The calibrated controllers achieved higher offline balanced accuracy (90.6% against 73.1% for the best controller of each paradigm), but completion rates did not differ significantly between paradigms, and the highest completion rate was achieved by a calibration-free controller. Calibrated controllers moved faster on successful acquisitions, partly because of their individually fitted speed mappings, though not significantly after correction for multiple comparisons. However, every calibration-free controller produced more direct and stable trajectories than every calibrated controller, even after adjusting for cursor speed. Offline accuracy did not predict completion rate across controllers or within participants, and across paradigms higher offline accuracy was associated with poorer trajectory quality in 15 of 16 participants. Without any calibration data from the end user, a model trained across a large population matched calibrated control in completion rate and exceeded it in trajectory quality. The offline accuracy gained through calibration should therefore not be taken as evidence of a closed-loop benefit.

arXiv AI Papershace 27 días

Table Serialization Determines Which Relations Language Models Preserve

We study how text serialization affects table lookup in instruction-tuned language models. Our diagnostic asks the model to find the row containing a specified value under one named column, then return the value under another named column in that same row. We render the same synthetic 256-cell tables in row-major form and in column-major form with each header placed beside its values, while varying the table aspect ratio across five shapes. Across three models, the better format changes with table shape: row-major performs better on tall tables, whereas column-major performs better on wide tables. At 64 x 4, row-major leads by 42.3-54.0 percentage points; at 4 x 64, column-major leads by 35.0-59.0 points. Mapping wrong answers back to their source cells reveals a complementary error pattern: row-major tends to preserve the correct row but lose the target column, while column-major tends to preserve the correct column but lose the row. We use the term relational locality to describe this pattern: serialization keeps one relation locally available while making the other depend on positional alignment. A separate non-tabular ordering experiment supports this interpretation. Thus, apparent width-related failures in text-serialized tables depend on linearization, not table shape alone.

arXiv AI Papershace 27 días

Who Gets Unmasked? Sampler-Induced Bias in Diffusion Language Models

Diffusion language models (dLLMs) generate by gradually unmasking a canvas, so their samplers decide not only which token to write but also when to commit it. We show that this second decision changes who appears in generated text, a sampler-induced bias on top of the model's own. Common commit rules, including LLaDA's default, commit the positions whose sampled tokens are most probable; this peeking favors majority options. To separate the sampler from the model, we read the model's belief about a fork, such as a protagonist's gender, in one forward pass, and show that this belief matches exact sampling from the model. Measured against it, peeking samplers on LLaDA and Dream amplify occupational gender stereotypes and collapse opinion distributions, and confidence-based ordering shifts gender-balanced occupations toward men, more so under faster parallel decoding. We propose Fork-First Sampling, which decides the fork before anything else is written: it follows the belief or any target distribution, improves fluency, and avoids the stories that remark on the protagonist's gender, which prompt-based fixes produce, at the cost of one forward pass. Fairness evaluations of dLLMs should report the commit rule.

arXiv AI Papershace 27 días

Cooperation Without Shared Rewards via Reciprocal Q-Augmentation

General-sum games are more challenging than fully cooperative or adversarial settings because agents may deceive or exploit one another. Achieving high social welfare requires sustained cooperation, while a single defection can drive agents toward a welfare suboptimal Nash equilibrium. Moreover, assuming access to other agents' rewards or internal states is often unrealistic and implicitly introduces additional cooperation into the setting. To address this issue, we introduce Reciprocal Q-Augmentation (RQA), a method that uses a latent-variable opponent model to augment the Q-function with estimates of how one's actions affects other agents. RQA allows agents to learn both cooperative and defective policies using only their own Q-function. We show that, in social dilemmas, agents that all follow the cooperative policy of RQA learn to cooperate faster and reach higher levels of cooperation than fully cooperative algorithms. Moreover, a single RQA agent that switches appropriately between its cooperative and defecting policies can induce cooperation in agents trained with standard RL algorithms, which would otherwise end up defecting. We evaluate our approach on the Iterated Prisoner's Dilemma, Iterated Traveler's Dilemma, Iterated Stag Hunt, and CleanUp-Lite. Our experiments show that the algorithms implementing RQA outperforms fully cooperative methods with shared rewards and enables cooperation with algorithms that otherwise fail to reach high social welfare.