Searcharxiv⌕ Search

arXiv subjects

Shashank Raj

Publications and source records attributed to Shashank Raj.

3 recordsLinked to original sources

Hardening Agentic Web Populations Through Multi-Criterion Competitive Co-Evolution: Lessons from Wargame Strategy Optimization

Agents on the open web will face adversaries that keep adapting, so a defense that is only tested once will eventually be found and broken. We propose treating jailbreak attacks and safety guardrails as two populations that evolve against each other, rather than as a fixed attacker probing a fixed defense. This idea comes directly from wargame strategy optimization, where two-population competitive co-evolution with alternating evolution cycles and cross-play evaluation has already been shown to produce strategies that are robust to a moving opponent, and where a companion line of work has shown that the same machinery can measure how much competitive pressure a population must absorb. However, real-world applications can never rely on a single criterion as a key performance indicator, rather must use multiple conflicting criteria, such as, cost and efficiency. We describe how this mechanism transfers to language model safety, argue why the resulting multi-criteria, competitive and coevolutionary arms race is a genuinely networked, population-level problem rather than a two-agent toy setting, and lay out the open problems that stand between the wargame version of this idea and an agentic web version of it.

cs.AI↗

EvE: An Alternate Optimizer to Adam

Adam and its variants dominate neural network training, but a single run only reveals whether a configuration works well after most of its budget is spent, a poor fit for hyperparameter or architecture search, where configurations must be ranked cheaply and pruned early. We introduce EvE (Evolutionary Explorer), a steady-state, population-of-four differential evolution (DE) optimizer with a targeted Adam fallback: each iteration proposes one candidate via DE, running a short burst of gradient descent only if the DE step fails to improve on the incumbent. Selection is greedy, so on a deterministic objective the best-so-far value is provably monotone non-increasing, and since gradients are used only as a targeted rescue, per-iteration cost stays within a constant factor of a single Adam step regardless of dimension. Under a fixed, evaluation-cost-matched budget, EvE wins or ties Adam on 76% of 70 (problem, dimension) cells across seven scalable benchmarks up to one million variables. On three real neural-network tasks (an MLP on MNIST, and LoRA fine-tuning of a 1.5B-parameter language model on two datasets) EvE finishes the same charged budget 1.7-3.9x faster, at a modest cost in final quality (about one accuracy point on MNIST, 9-11% higher relative test loss on the two fine-tuning tasks; on GSM8K, Adam is about 5 accuracy points more accurate, and fine-tuning lowers accuracy below the base model for both). Inside successive halving on UCI Adult, EvE completes hyperparameter and architecture searches 3.1-3.5x faster, ranking configurations about as consistently with Adam as Adam does with itself across seeds (Kendall's tau 0.66-0.69). EvE is not a total replacement for Adam as a final-stage trainer, but a fast, gradient-aware proxy for the search-heavy, budget-constrained regime one level up.

cs.LG↗

EvoSort: A Genetic-Algorithm-Based Adaptive Parallel Sorting Framework for Large-Scale High Performance Computing

We present EvoSort, a general-purpose adaptive parallel parallel sorting framework accessible at the Python level. EvoSort employs a Genetic Algorithm (GA) to automatically discover and refine critical parameters, including insertion sort thresholds and algorithm selection (e.g., versus LSD radix sort). By adapting continuously to input data and system architecture, EvoSort provides a drop-in replacement for standard Python routines like NumPy and Pandas. Experiments up to10 billion elements across nine data distributions and two hardware platforms demonstrate that EvoSort consistently outperforms competing methods. Results show speedups of up to 225x, exemplifying a powerful auto-tuning solution for large-scale data processing.

cs.DC↗