Tema

Código abierto

1634documentos

158últimos 7 días

Ranking Agreement Does Not Reveal Paragraph-Edit Agreement in Two Released Paper Acceptance Predictors

A fast acceptance classifier could select revisions for a slower evaluator. We ask whether agreement on existing papers supports that use. We compare a classifier of word and document features with two released text-only acceptance predictors fine-tuned from the same language model with three billion parameters. For 198 papers from the International Conference on Learning Representations, we compare model rankings of the original papers and of paragraph rewrites screened automatically for unchanged facts, claim strength, and attribution. The classifier ranks original papers closely with one predictor and moderately with the other, but shows no detectable agreement with either on which rewrites raise scores. The tests specified in advance used reduced numerical precision. Rounding error dominated the small score responses. We therefore rescored the released weights in full 32-bit precision as a post hoc check; edit agreement remained near zero. At this precision, when each predictor chooses among five rewrites per paper, its average raw score is under two points out of 100 higher than with random choice. The evidence covers presentation rewrites and two open predictors from one family; transfer to costly evaluators remains untested. Revision selectors should therefore be checked against the intended evaluator on the revisions they rank.

arXiv AI Papershace 8 días

FedFiOT: Fisher-Weighted Optimal Transport for Model Merging in One-Shot and Few-Round Federated Learning

One-shot and few-round federated learning (FL) reduce communication burden by constructing a global model within one or a few communication rounds, but often achieve lower performance than conventional multi-round FL. Without frequent synchronization, client models may drift apart, causing neurons that learn similar features to occupy different positions across clients. At the same time, local data heterogeneity can cause corresponding parameters to differ in their importance to each client's predictions. Together, these challenges cause direct averaging to combine mismatched neurons and assign equal weight to parameters despite differences in their importance. We propose FedFiOT, a Fisher-weighted optimal transport framework for one-shot and few-round FL that leverages Fisher information to quantify parameter importance and guide neuron alignment and model aggregation. FedFiOT jointly optimizes neuron correspondences and global model parameters through alternating minimization of a shared Fisher-weighted objective. Theoretically, we show that FedFiOT's optimization procedure monotonically decreases the layer-wise merging objective and establish a stationarity bound that quantifies the effects of client heterogeneity and nonuniform Fisher weighting.Experiments across multiple datasets demonstrate consistent improvements over competing baselines in both one-shot and few-round federated learning settings.

arXiv AI Papershace 8 días

Continual Classification Beyond the Kernel Regime: Harnessing the Sparsity Bias of L2 Regularization in Diagonal Linear Networks

We study logistic regression for continual learning with linear predictors in a high-dimensional statistical setting. Existing theoretical work has largely focused on continual linear regression with variants of L2 regularization, motivated by their analytical simplicity and connection to the kernel regime of neural networks. We first derive the optimal L2 regularization strength for continual linear classification and characterize its generalization performance, recovering behavior analogous to prior results for continual linear regression. Next, we examine the effect of L2 regularization in deeper models using a minimal two-layer diagonal linear network. In the single-task setting, L2 regularization on the weights of such models is known to promote sparsity in the resulting predictor, yielding a rich, sparse feature-learning regime beyond the kernel regime (a similar effect arises in two-layer ReLU networks). However, in continual learning, where L2 regularization is typically centered on previous-task weights, this sparsity bias is no longer preserved. We therefore propose a weighted variant of L2 regularization that extends this beneficial sparsity bias to continual learning. We show theoretically and empirically that, for a sufficiently sparse teacher, our variant converges substantially faster than directly learning a linear predictor with conventional continual L2 or L1 regularization, trading some long-horizon bias for markedly improved performance over moderate task horizons.

AWS Machine Learning Bloghace 8 días

Four layers of context engineering for production AI agents: How Deep Insight applies them in working code

In production AI agents, context management is the real bottleneck. This post presents a four-layer context engineering framework (architecture, prompts, file-based tools, and verification agents), implemented in working code from Deep Insight, an open source multi-agent data analysis solution on the Strands Agents SDK and Amazon Bedrock AgentCore.

arXiv AI Papershace 8 días

Turns Matter: Advancing Streaming Video RL via Turn-Level Credit

Streaming video understanding requires models to repeatedly decide whether to respond or continue observing. Recently, Group Relative Policy Optimization (GRPO) has been applied to this setting, with existing approaches emphasizing reward design while retaining a single trajectory-level advantage across turns. Such shared credit can reinforce redundant replies after earlier successes and discourage useful follow-ups after earlier failures. We propose TurnWise, a turn-level GRPO framework that aligns learning with individual streaming decisions. TurnWise addresses the mismatch between trajectory-level feedback and turn-level interaction, promoting informative responses and reducing redundancy. Specifically, turn-level credit assignment uses silence-completed prefix scoring to construct group-relative advantages from each decision's remaining return, separating its learning signal from earlier rewards. Turn-mean policy optimization averages token losses within each turn and then across turns, giving response and waiting decisions equal weight regardless of output length. These complementary designs improve streaming policy learning without a learned critic or additional rollouts. Extensive experiments show our method outperforms prior RL approaches for streaming video understanding.

arXiv AI Papershace 8 días

FPTR: Feasibility-Preserving Transactional Refinement for Deadline-Constrained Joint Beam and Resource Allocation

Short-interval wireless schedulers must return a complete, feasible beam-and-resource allocation before each execution deadline, and a late or invalid output gives no utility in the current control cycle. Searching longer can increase transmitted traffic, but it may also miss the deadline or leave only an infeasible intermediate solution. We propose Feasibility-Preserving Transactional Refinement (FPTR), which always keeps a validated feasible allocation, the incumbent. Each refinement stage builds a separate candidate and leaves the incumbent unchanged. A candidate replaces the incumbent only if it is complete, passes the feasibility validator before its stage cutoff, and strictly improves the objective; otherwise it is discarded. Four refinement stages use this rule: buffer-aware resource selection, compatibility-group (CG) user sharing, beam-mask rebuilding from remaining demand, and joint reassignment of two resources. On 150 fixed synthetic instances, the full pipeline (Full) raises traffic by 3.83% on average over a lightweight beam-first reference and by 1.79% over its Base constructor. In a separate suite with matched inputs, Full exceeds six independent search baselines (ALNS, tabu search, GA, simulated annealing, iterated local search, and GRASP) by 6.68-8.35%, where outputs later than 100 ms receive zero utility. All 750 Full runs in the internal suite returned feasible allocations, and none exceeded 100 ms. Separating mandatory output construction from optional refinement lets spare computation time improve the allocation without endangering the incumbent. The open-source implementation supports independent reproduction.

arXiv AI Papershace 8 días

Hardwired Distributed Processing Units for Inference: Neural Decisions at the Sensor that Free the Host

We show that a hardwired distributed processing unit (HDPU) can take a neural decision at the sensor and so remove the inference from the host. Built for zebra-crossing detection on a low-cost Artix-7 FPGA, the unit decides on every camera frame in a fixed 2,269,477 clock cycles (34.04 ms depends upon Fpga clk ), inside the 37.49-ms frame period, and on the board it returns the same scores and decisions as its bit-exact software model on all 639 test images. The whole detection path, from camera pixels to decision, takes 1,814 LUTs, with no processor, no operating system and no full-resolution frame store. When the unit answers instead of reporting "not sure", 95.7% of its answers on street photographs are correct, and a hardware contrast stage lifts accuracy on camera-like dashcam frames from 47.7% to 78.2%. The host is spared all of the inference: 8.13 ms of a core in every frame period, where a full-precision ResNet-18 would need more than a frame period even on 16 threads. It also receives 16 bytes per frame instead of 614,400, 38,400 times less. The unit is an 80x60-pixel pipeline feeding a four-layer binarized CNN with 93,408 one-bit weights, verified bit-exactly from a Python model through RTL simulation to the board. Earlier HDPUs did pre-processing (edges, corners, steering); this one shows that the decision itself can move to the sensor.

arXiv AI Papershace 8 días

EviSeek: An Evidence-Centric Agentic Framework for Embodied Active Information Seeking

Active embodied question answering requires agents to acquire evidence through viewpoint changes and physical interaction. The central challenge is to avoid undirected interaction: taking plausible actions without specifying what evidence they should reveal for answering the question. Action plans and accumulated histories alone can leave the informational purpose of an interaction implicit. We introduce EviSeek, a training-free framework that makes question-derived evidence demands explicit acquisition objectives, linking observation-conditioned actions and selectively retained evidence to the information the agent seeks. On 3,436 ESI-Bench questions, EviSeek improves accuracy over the Single-model agent by 7.1 percentage points with Qwen3-VL-32B and 3.7 points with Gemini 3.1 Pro, while improving visual-support-weighted accuracy and reducing mean token usage. These findings support making the informational purpose of interaction explicit, with action selection and evidence retention organized around what the agent needs to learn to answer the question.

arXiv AI Papershace 8 días

KolTa: A Physics-Informed Active Learning Framework for Formulation Discovery with Limited Data

Finding high-performing formulations is difficult when few have been measured and experimental budgets are limited. We propose KolTa, an active learning framework that selects batches to discover the top 5% of formulations at a target temperature under a fixed query budget. KolTa combines a three-stage predictor of component contributions, role-conditioned interactions, and anchored temperature response with task-specific soft physics constraints. Its Physics-Residual-Calibrated Upper Confidence Bound (PRC-UCB) acquisition rule combines predicted utility, ensemble disagreement, and a target-temperature physics residual, with nonnegative exploration weights fitted to out-of-fold signed errors. We evaluate the framework on three measured tasks and one simulated task covering binary-mixture viscosity, drug solubility, ionic-liquid viscosity, and electrolyte conductivity. KolTa ranks first or second in mean area under the learning curve (AULC) on every task and outperforms seven of the eight comparator strategies in paired tests, winning 75 of 78 paired comparisons across tasks and seeds against those seven strategies. Across the three measured tasks, its largest gap to the best mean AULC is 0.032, compared with at least 0.056 for every comparator. On Drug, reaching 80% average recovery of the remaining targets across drugs requires an estimated median of 348 additional formulation queries, about 18% fewer than the fastest comparator. Researchers can adapt the framework to diverse formulation problems through component roles and physical constraints.

arXiv AI Papershace 8 días

Flexible Intensities Matter: A Comprehensive Re-evaluation of Hawkes Processes and Neural Temporal Point Processes

Temporal point processes (TPPs) are the canonical framework for event sequence data, with applications spanning seismology, social media, and electronic health records. Recently, neural TPPs have been reported to substantially outperform classical TPPs, such as Hawkes processes, but these comparisons pitted flexible neural models against Hawkes processes in their most restricted form, and did not consider large-scale medical data. Here, we revisit this comparison through a systematic evaluation of Poisson and Hawkes processes of increasing flexibility against neural TPPs, on five established benchmark datasets and on two large-scale medical evaluation tasks derived from UK Biobank disease histories and MIMIC-IV ICU records, under autoregressive next-event prediction. First, the previously reported gap between Hawkes processes and neural TPPs largely disappears once Hawkes processes are equipped with flexible, learnable baselines and kernels. Second, the flexibility of the intensity parametrization also limits prior neural TPPs: a Transformer with a spline-based intensity head outperforms previous intensity-based neural TPPs and is on par with the intensity-free model. Decomposing the log-likelihood into a time term p(t) and a type term p(d t), we find that this flexibility advantage lies almost entirely in the time density: more flexibility does not improve the type term. On these benchmarks, the gains of neural TPPs thus lie mostly in modeling when events occur, not which. Third, our results underscore the value of complex datasets for evaluating TPPs: only on the MIMIC-IV ICU records do neural TPPs retain an advantage in the type term. Our results inform both future method development and model choice. We release our framework, TorchPP, as an open-source package with consistent implementations of classical and neural TPPs.

arXiv AI Papershace 8 días

EnzymeRSI: A dual-loop recursive self-improvement system for enzyme design

Improvement in enzyme engineering is usually pursued by optimising which candidates to assay within a fixed model and workflow; when the bottleneck arises from a mismatched method or a failing workflow, that route is difficult to escape. We present EnzymeRSI, a dual-loop system for recursive self-improvement (RSI). The outer loop evolves harness assets without changing model weights, the inner loop develops prediction and selection algorithms under controlled conditions, and a cloud laboratory system is specified to close the physical loop with quality-controlled feedback. By updating its prediction strategy through iterative comparison, the outer loop raised the mean development-set Spearman correlation on ProteinGym by 0.044 across five assays, reaching 0.335 on CD19 and 0.683 on OPSD (rhodopsin); of the two first places, only CD19 was produced by the outer loop itself. In the self-improvement of the ThermoMPNN algorithm the inner loop reached a PCC of 0.849, and on TadA-Bench it reached a Spearman correlation of 0.307 in 1.13 h. In three prospective wet-lab tests of the system's experimental decision-making, 10 of the 32 candidates that had not been pre-specified for the luciferase RLuc showed at least twice the wild-type activity; a recommended variant of the cytidine deaminase A3A raised 5mC conversion to 90.2%; and path selection in evolution raised the catalytic efficiency of the DNA polymerase KOD-E on a modified substrate to 31.1 times that of the parent. By treating the organisation of the research workflow and the development of algorithms as a single falsifiable dry-to-wet loop, this work offers an evolutionary paradigm for moving beyond the blind spots of a fixed method and for autonomous enzyme engineering.

arXiv AI Papershace 9 días

Diversity-Aware Experience Replay via Statistical Leverage Scores

Off-policy deep reinforcement learning trains on random samples from a replay buffer of past experience. In physical robot settings, that buffer is dominated by routine: thousands of near-identical transitions from normal operation, while the rare events that define the edges of the task are rarely sampled. We propose scoring every stored transition by its statistical leverage, which measures how unusual it is relative to the buffer's own data, computed from the stored numbers alone, with no labels, rewards, or value network. We draw each mini-batch from a mixture of this score and uniform sampling. First, the natural way to build the score along the directions where the data varies most turns out to be blind when actions are stored as one-hot indicators, because indicator columns always win the variance ranking; we instead select the feature columns with the heaviest tails (largest kurtosis) where small far-away populations are revealed. Second, the importance weights that prioritized replay uses to keep gradients unbiased cancel the method exactly: with full correction, training matches uniform sampling, so we drop the correction and deliberately optimize the rebalanced objective. Third, when the rare situations of a log are relational, visible only in how a stretch of behavior relates to its goal, not in any single stored coordinate-per-transition scores are blind; applying the same tail rule to short trajectory windows described relative to their goal restores the signal, and on a three-joint arm that must push an object around an obstacle it raises the rare-task success from 0.49 to 0.69 against a labeled-oracle ceiling of 0.74.

arXiv AI Papershace 9 días

Modality-Aware Expert Pruning for MoE-Based Multimodal Large Language Models

Mixture-of-Experts (MoE) enables multimodal large language models (MLLMs) to scale capacity efficiently, but expert parameters dominate memory even though only a few experts are activated per token: they account for over 90% of model size in modern MoE-MLLMs (e.g., 54 GB out of about 58 GB in BF16 for InternVL3.5-30B-A3B and Qwen3-VL-30B-A3B). Expert pruning has emerged as an effective compression strategy, but existing methods aggregate importance uniformly across tokens, ignoring that the same expert may serve different roles for vision versus language processing. To address this, we propose MAEP (Modality-Aware Expert Pruning), a training-free framework that decomposes expert importance by modality in a single forward pass. MAEP introduces (1) Delta-H Output (ΔH), a redistribution-aware metric measuring the MoE output change when an expert is removed, and (2) low-attention vision tokens as a vision-side pruning signal that is dataset-stable: its expert-importance ranking remains stable across different datasets. Text-side importance serves as a preservation signal while vision-side importance serves as a pruning signal, and experts are ranked globally across layers. Experiments on three MoE-based MLLMs across multimodal and text benchmarks show that MAEP outperforms modality-agnostic baselines on the majority of multimodal benchmarks while remaining competitive on text-only tasks, reducing the BF16 expert weight footprint by about 27 GB (about 47% of total memory) so that the full weight footprint of an approximately 58 GB model fits within a single 40 GB GPU. Code is available at https://github.com/nota-github/MAEP.

arXiv AI Papershace 9 días

Does Your Trial Simulator Know What the Drug Does? An Intervention-Blind Test of Interventional Validity on 7,207 Registered Trials

Patient world models are increasingly proposed as simulators of clinical trials, and recent surveys rank their capabilities on a ladder from temporal prediction to counterfactual rollouts. Position on that ladder is currently assigned by reading papers rather than by measurement. We turn the counterfactual rung into a measured quantity. From 30,119 completed phase 2/3 trials with results posted to ClinicalTrials.gov we construct 9,996 audited within-trial contrasts from 7,207 trials, and we score a simulator on how much of its accuracy depends on knowing which intervention was tested. The instrument is an intervention-blind reference: the same model, trained on the same trials, with every intervention-identifying field withheld. Interventional skill is the error the full model removes relative to that reference. On a temporal split (878 test contrasts from 655 trials) a registry-trained gradient-boosting simulator removes a fifth of the error of a trivial baseline, but its interventional skill is -0.12 (95% CI -0.21 to -0.05): withholding the intervention makes it better, and no alternative featurisation, stratum, temporal cut or same-molecule retrieval yields an interval above zero. A frontier language model reading only the registered protocol has interventional skill 0.20 [0.08, 0.31]; smaller and open-weight models sit at the limit of detection. Perturbation tests show the large model uses the intervention as such: swapping the arms reverses the sign of its prediction in 86% of contrasts. The blind reference is itself not drug-blind (a language model recovers the withheld drug class 45% of the time from the blind prompt), so interventional skill is a conservative lower bound. A reliability layer shows that ranking by predicted error lowers it but that calibrated error control does not transfer under temporal shift. Benchmark, code, prompts and per-call model outputs are released.

arXiv AI Papershace 9 días

Selective, Risk-Controlled Emotion Forecasting in Conversation: From a Persistence Barrier to Departure Detection with Conformal Guarantees

Forecasting emotion in conversation is increasingly framed as predicting the next emotional state's value. We show this targets a hard quantity in a state-observed testbed and propose a learnable, deployable reformulation instead. On valence-arousal-dominance trajectories from a dyadic corpus, repeating a speaker's own previous state sets a persistence baseline that no frozen-encoder correction meaningfully improves upon and a state-space filter exceeds; the floor requires the historical state to be observed, since an estimated anchor collapses persistence below a direct forecaster. What survives is the timing of a departure from persistence, learnable on three of four corpora and near chance on the highest-base-rate corpus, a negative result we report. We recast the task as selective departure forecasting: a lead-time-weighted metric with a leakage protocol, and commitment policies whose best choice switches with the departure rate. A dialogue-level conformal risk control bounds the expected loss of committed predictions, meeting the target in all twelve configurations tested, though the guarantee is bought through abstention, with coverage and alarm recall falling sharply on the hardest corpus. One tested language model's confidence fails as a ranking signal where another succeeds, a model-dependent failure not yet attributable to family versus scale. Code and result logs are available from the corresponding author upon request.

arXiv AI Papershace 9 días

RECAP: Context-Aware Prediction Recycling with Request-Local and Persistent Memories for Multimodal Speculative Decoding

Recycling a target model's own predictions offers a training-free source of proposals for speculative decoding. In vision-language models, however, existing recycling indexes predictions by the last token alone, conflating predictions computed under different images and prefixes; we find that such reuse fails most often at image-sensitive decoding states. Longer keys reduce this aliasing but match fewer states. We introduce , which stores target predictions under one-, two-, and three-token keys: contextual memories live only for the current request and are thus implicitly conditioned on its image, while token-level memory persists across requests to retain coverage. At each lookup, entropy-confidence weighting fuses the retrieved predictions according to their key specificity and concentration. Best-first search composes the fused transitions into a candidate tree, supplemented by suffix-matched continuations, and one target pass verifies the tree under greedy decoding. Without training or an auxiliary draft model, \ achieves mean speedups over autoregressive decoding of 1.66and 1.56across seven single-turn benchmarks on Qwen2.5-VL-7B and LLaVA-1.6-7B, exceeding the strongest training-free baseline, Token Recycling (1.51and 1.37). Our implementation is available in https://github.com/Senmo996/RECAP-official-code.

arXiv AI Papershace 9 días

CellCanon: An Agentic Cellular World Model for Prediction, Explanation, and Observation-Driven Updating

Biological discovery requires using molecular knowledge and new measurements to infer responses beyond the conditions already observed. We introduce CellCanon, the first agentic cellular world model to unify single-cell expression prediction, evidence-grounded explanation, and observation-driven updating. Its predictive core reuses condition-level biological evidence across gene-specific numerical readouts to guide single-cell expression generation. A shared world state links predictions, acquired measurements, and source-linked claims, supporting explanation and revision. On 339 held-out SciPlex3 conditions across three cell lines, CellCanon improves differential-expression AUPRC and Macro-F1 over the best baseline for each metric by 63.3% and 17.3%, respectively, and direction Macro-F1 by 7.2%. Relative to gene-wise reasoning on matched drug-cell cohorts, measured language-model token use falls by 99.77% for Predict and 98.41% for Explain. On the source-grounded benchmark, Explain correctly answers all answerable questions with supporting proofs and identifies all insufficient-evidence cases. In simulated experimental feedback, Update uses one measured source context per drug to exceed the best fine-tuned baselines in differential-expression AUPRC and Macro-F1 without changing model weights. Together, these capabilities support a cumulative account of cellular responses, with predictions and biological judgments that can be revised as evidence accumulates.

arXiv AI Papershace 9 días

AI-Assisted Classification under Correlation Neglect and Trust

When does an AI assistant improve human decision-making, and when does it hurt? We argue that the answer depends not just on AI accuracy but also on how much its evidence overlaps with the human's and how the human combines the two. A worker makes a binary decision by observing her own signal and receiving a recommendation from an AI. We develop a human behavioral model with two primitives: her awareness of the overlap and her trust in the AI. Our analysis gives a closed-form phase diagram over AI capability and overlap, with regions of complementarity, impairment, and automation. A worker who neglects the overlap (correlation neglect) can be made less accurate by a more capable AI, double-counting the shared evidence. Trust reshapes the regions - undertrust may compensate for correlation neglect, so that the trust level maximizing accuracy depends on the deployment parameters. Empirically, we identify the two model parameters by pairing the same workers with different AIs, and break the accuracy loss into a correlation-neglect cost and an undertrust cost, one tied to reducing overlap on the AI side, the other to calibrating trust on the human side. On ChatBench, AI assistance raises accuracy by 21 points, yet workers apply only about a quarter of the Bayes-rational weight to AI information; GPT-4o falls in the automation region and Llama-3.1-8b stays at the complementarity boundary; and calibrating trust recovers about 2.6 points for GPT-4o but almost nothing for Llama-3.1-8b.

arXiv AI Papershace 9 días

CARTBench: Rubric-Based Evaluation of Shopping Advice for Complex and Ambiguous Requests with Timelines

Large language model (LLM) shopping assistants now recommend products in multi-turn conversations. However, reliable evaluation faces Data scarcity and Difficulty Standardizing Criteria. To address these obstacles, we introduce CARTBench for CART (Complex and Ambiguous Requests with Timelines). For Data scarcity, we curate cases from real commercial shopping needs across 17 retail domains, pairing timestamped dialogue with 1,603 product records. For Difficulty Standardizing Criteria, we develop case-specific rubrics guided by Ideal Response Principles, distilled from excellent replies manually selected from successfully completed orders. These principles also guide Principle-Guided CART Prompting, our structured recommendation strategy. The experimental benchmark contains 1,328 expert-annotated criteria across Core, Excellence, and Safety. To answer the CART question, we evaluate 7 flagship commercial API models, including GPT-6.1-Sol and Claude-Opus-5, and 35B+ parameters open-weight models. In the first full-suite evaluation under the frozen rubrics, 3 of 10 models exceed 90% on Core, while none exceeds 45% on Excellence. Therefore, we identify an understanding-to-execution gap between required behavior and high-quality purchase advice. To examine these limitations, we diagnose shared failures in product evidence and unresolved needs, linked to changing requirements and decisive unknowns. Code and data are available at https://github.com/Da1yuqin/CARTBench.

arXiv AI Papershace 9 días

PEARL: Prediction Error-Adaptive Regularized Learning for Selective Forgetting under Partial Preference Drift

User preferences shift as needs, context, and tastes evolve. This matters for personalized recommendation, LLM response generation, and RLHF-trained reward models, which can become miscalibrated as preferences drift. Existing non-stationary bandit methods forget uniformly across all dimensions, but real preference shifts are typically partial: some dimensions go stale while others remain valid. Neural contextual bandits accumulate confidence monotonically via the Gram matrix, with no mechanism to direct uncertainty where predictions have gone wrong. We propose PEARL (Prediction Error-Adaptive Regularized Learning), which reverses the Gram update along feature directions where predictions are surprisingly wrong, while leaving confidence intact elsewhere. We prove that (i) any non-adaptive policy suffers linear regret after a preference shift, (ii) no fixed exploration rate achieves low regret in both stationary and non-stationary regimes, and (iii) PEARL's cumulative regret scales with the number of shifted users N_s, not the total population N. On PRISM, a personalized LLM response selection benchmark (1,500 users, 21 LLMs), PEARL beats greedy by +4.0 points and the best neural bandit baseline by +2.5 points (p<0.001), while performing on par with greedy when preferences are stable. It beats sliding-window and discounted approaches by 3 to 10 points, showing that selective forgetting outperforms uniform forgetting. The selection policy is a ~100K-parameter MLP that runs in milliseconds on CPU, leaves LLM weights frozen, and works with any API-based model.