arXiv subjects

Md Najmus Swaqeeb

Publications and source records attributed to Md Najmus Swaqeeb.

7 recordsLinked to original sources

arXiv2026

One-Step Curvature Probes Miss the Fitting Operator: Retained Capacity and Terminal Null-Space Correction for Continual Learning

A one-step curvature probe evaluates an initial direction, whereas continual learners are judged after reaching comparable new-task fit. In an overparameterized linearization, projected gradient descent converges to $Δ_P=PJ^\top(JPJ^\top)^{-1}r$, and its squared-displacement inflation is exactly the reciprocal of the retained fitting capacity $c_P(r)$. More generally, the terminal old-task quadratic ratio factorizes as $1/[c_P(r)G_{\rm end}(P,r)]$, where $G_{\rm end}$ compares curvature along endpoint directions. In the rank-one case, $G_{\rm end}$ equals the one-step probe gain; for multiple outputs, the two gains can differ. The terminal quadratic also separates into a curvature-optimal fitting floor and an algorithm-dependent null-space excess, motivating terminal null-space correction, which preserves linearized new-task outputs on its Jacobian batch. Controlled checks validate the local quadratic and show that projection can greatly reduce matched-norm curvature while barely changing terminal forgetting. Across common-threshold configurations, projection yields the larger signed old-task loss change in 73/99 matched pairs, retained fitting capacity falls with rank, and fixed-rank comparisons separate terminal forgetting even when probe gain is approximately matched. On Permuted MNIST and Split CIFAR-100, terminal correction decreases signed old-task loss in 166/180 method--dataset--seed pairs under the all-seed intention-to-correct analysis; because acceptance and outcome reporting use the same held-out split, this result is descriptive and test-conditioned. Overall, terminal cost depends jointly on retained fitting capacity, endpoint-direction curvature, and the null-space component selected by optimization.

cs.LG↗

arXiv2026

Certified Predictive Value-of-Advice Gating for Cost-Aware Language-Model Guidance in Reinforcement Learning

Language-model advice can accelerate reinforcement learning, but calls are costly and returned actions may be stale or wrong. We formulate advice acquisition as a response-contingent metareasoning problem: before querying, the controller predicts possible parsed responses, evaluates the decision and declared continuation that would follow each response, and queries only when a lower confidence bound on predictive value exceeds the priced cost. Execution is governed separately by an action-specific certificate. Under explicit assumptions, certified advice is near-optimal, a wrapped learner inherits fallback regret only under intervention stability, and conservative allocation loses at most the declared query-value estimation error relative to a myopic oracle. On BabyAI, a proxy-calibrated controller with Qwen2.5-1.5B and 7B advisors improves GoToObj return over no querying by 0.029 +/- 0.016 and 0.030 +/- 0.015 across 20 seeds while reducing calls by more than 97% relative to always-query. GoToLocal is a null result. Exactly matched-call tests show an advantage over random placement only for the 1.5B advisor and no advantage over an equal-budget early schedule. Mondrian calibration improves decision-relevant empirical coverage from 0.47 to 0.85, still below the 0.90 target, while the formally covered radius is vacuous. The demonstrated benefit is therefore robust sparse advice volume on a useful task, not a proven per-state placement advantage.

cs.LG↗

arXiv2026

Spectral Tail Interventions in Decoder-Only Language Models: Reasoning-Sensitive Weight Structure from Controlled Surgery

Weight-space structure often correlates with language-model behavior, but correlation alone does not establish computational involvement. We study concentrated upper spectral tails in decoder-only transformers through controlled interventions. At a fixed relative offset, we derive a finite-width conditional bound linking the inverse participation ratio of squared singular values to central pre-softmax logit kurtosis. We then define a pointwise query--key ($QK$) product-tail target and compare independent factor surgery with a product-targeted factorization that preserves native attention computation. Across three base checkpoints and five reasoning benchmarks, plus an instruction-tuned Phi checkpoint analyzed separately, the learned-tail edit is more damaging than the mean of five fixed spectrum-matched Haar controls in all 20 model--task cells. Eighteen paired contrasts remain significant after Holm correction, while two are directional but inconclusive. Product-targeted factors attain higher held-out tail-subspace fractions, providing an empirical bridge between product- and factor-level interventions. Component isolation identifies contributions from $QK$, value--output, and multilayer-perceptron blocks, although the theorem covers only $QK$. In separate studies, inverse participation precedes pooled accuracy transitions under a matched crossing rule, and residualized tail-aware low-rank adaptation (LoRA) reaches targets earlier than standard LoRA and PiSSA while final-score intervals overlap. Conclusions are restricted to the evaluated checkpoints, layers, tasks, interventions, and controls.

cs.LG↗

arXiv2026

Opportunity Is Not Realizability: Selection-Valid Diagnostics for Multi-LLM Routing

Oracle routing measures how much a pool of language models could gain from per-query selection, but the diagnostic has two flaws: testing against a best fixed model selected on the same examples invalidates paired inference, and a full-information oracle sees outcomes no deployable router observes. We separate three estimands (outcome-oracle opportunity, the Bayes-optimal gain from a declared pre-answer signal, and the held-out gain of a learned router) and prove selection-valid confidence intervals that survive choosing the best fixed model or the best member of a router family, a signal-information sandwich, and a $(1-1/e)$ greedy guarantee for building compact pools from submodular complementary coverage. On eight checkpoints from six families over four benchmarks, selection-valid intervals certify a population oracle gap of $9.7$--$30.7$ points on every task, yet the strongest deployable prompt router recovers only $7.5$--$14.4\%$ of it, and the simultaneous interval for the best of eleven tested policies has lower limit zero throughout. The realizable share of oracle opportunity is small and certifiable: strong routers beat the best fixed model, and most of the gap remains.

cs.LG↗

arXiv2026

Stateful CARS: Exact Cross-History Reuse for Policy-Constrained LLM Agents

Tool-using language-model agents face constraints whose meaning changes with observations and prior actions. We study exact sampling from the model distribution conditioned on a hard stateful validator while reusing invalidity certificates across histories. Stateful CARS freezes a bank of sound state--continuation schemas within each attempt and removes every trajectory containing a certified continuation at a matching abstract state. An exact residual Doob transform samples from the resulting proposal. We give a checkable future-validity bisimulation condition, prove schema soundness, adaptive exactness, i.i.d.\ outputs, almost-sure termination, monotone acceptance, and compression invariance, and characterize computation by the number of reachable full-history product states. This number can be exponential for a history-dependent language model; the evaluated method therefore makes no generic finite-trie scalability claim. On enumerable workflows, its analytic law matches the valid conditional to $10^{-16}$ at validity probability $6\times10^{-8}$, whereas state-aware local decoding can be $0.97$ away. A matched comparison is negative: observation-keyed official CARS is cheaper in sampler steps (root/Stateful ratio $0.942$ $[0.934,0.951]$), and the Qwen comparison is null ($0.99$ $[0.90,1.08]$). Cross-history transfer helps only in an internal matched-key ablation ($1.27\times$). Thus the evidence supports exact schema-induced conditioning, not a systems advantage over CARS.

cs.LG↗

arXiv2026

CODS: Iterative Bellman-Residual Data Selection for Reusable Offline Reinforcement Learning

Offline reinforcement learning repeatedly trains policies from a fixed transition pool, making redundant data costly across seeds and hyperparameters, while naive subsampling can remove rare transitions needed for long-horizon credit assignment. We introduce CODS, a critic-guided selector that alternates between fitting an algorithm-matched critic and acquiring high-residual transitions before freezing a reusable subset. Unlike prioritized replay, CODS produces a static artifact; unlike one-shot residual selection, it refreshes scores as the critic changes. At a 10\% budget, CODS retains 96.6\% of eligible-pool performance across 20 valid D4RL task--algorithm cells. It exceeds ReDOR and OPER on 19/20 cells and every other subset baseline on 20/20; all six subset advantages remain significant under predeclared hierarchical inference with Holm correction. Holding total selector updates fixed, five acquisition rounds improve four representative cells by 11.23 points over one round and saturate thereafter. Equal-pass and equal-hour evaluations clarify that reuse, rather than a single-run speedup, creates the compute advantage. Mechanism and corruption interventions expose both useful sparse-reward enrichment and sensitivity to outliers. Finally, a whole-trace extension retains 95.4\% of pooled ALFWorld success and 96.5\% of pooled GSM8K exact match. CODS is therefore a reusable selection procedure, not a formal coreset guarantee.

cs.LG↗

arXiv2026

Finite Constant Frontiers and Auditable Regret Certificates for Average-Reward Reinforcement Learning

Average-reward reinforcement-learning regret is known up to logarithmic factors, but the numerical content of published guarantees is difficult to compare because probability mode, structural parameter, logarithmic normalization, prior information, and planning assumptions differ. We introduce a constant-aware comparison protocol and derive an explicit finite lower certificate for communicating MDPs. The construction is a binary tree of two-state blocks; its proof uses exact trajectory-level Bernoulli KL divergence and keeps action budget, diameter, occupancy, navigation cost, and terminal bias explicit. A common closed-form envelope improves the published coefficient $0.015$ across a finite frontier: $0.0200$ in a moderate regime and up to $0.0291$ under stronger action, diameter, and horizon conditions, a $94\%$ increase. The limiting coefficient is $\frac1{32}\sqrt{(A-3)/A}$. For upper bounds, we give an auditable composition rule for a span-constrained optimistic learner, but do not claim a coefficient while adaptive directional-variance and planning certificates remain open. We also formalize valid expectation conversion and constant comparability. Controlled diagnostics test diameter dependence, bonus-by-width interactions, span misspecification, and the finite lower certificate on its exact family.

cs.LG↗