arXiv:2606. 04039v1 Announce Type: cross Abstract: Neural-guided Ant Colony Optimization (ACO) suffers from a fundamental training-inference misalignment: policies are typically trained to generate static priors (e.
arXiv:2606. 15197v1 Announce Type: cross Abstract: Optimization modeling is inherently hierarchical, requiring a precise sequence of symbolic commitments.
MiLoop is a reinforcement‑learning‑based constructive framework for neural combinatorial optimization that propagates selective memory across rollout steps. By fusing current embeddings with historical memory before attention layers and applying adaptive gated updates afterward, it enables a shallow policy to learn dynamic embeddings without external solution labels or search‑space pruning. Experiments on four combinatorial optimization problems show MiLoop consistently generates high‑quality solutions for instances ranging from 100 to 10 million nodes, demonstrating strong generalization.
arXiv:2602.13691v2 Announce Type: replace Abstract: Recent advancements in Large Language Model (LLM) agents have demonstrated strong capabilities in executing complex tasks through tool use. However...
Agentic ESOpt proposes using evolution strategies (ES) instead of reinforcement learning to fine‑tune large language‑model agents for long‑horizon tasks. ES offers model scalability, flexibility, and better long‑horizon credit assignment, enabling full‑parameter optimization with minimal GPU memory. The framework samples parameter perturbations, evaluates agents with rewards, and updates online, achieving notable performance gains on WebArena‑Lite and in test‑time prompt‑parameter co‑evolution.
GRAPE is a two‑stage Bayesian optimization framework that first refines the local gradient posterior using a closed‑form acquisition function and then selects update directions by maximizing expected decrease conditioned on descent. The authors prove that the refinement stage monotonically reduces local uncertainty and that the progress‑aware direction converges to true steepest descent as the posterior sharpens. Empirical results show GRAPE achieves a 5.4× speedup on black‑box adversarial attacks and reduces final average regret by 3.8 log‑units on large language model prompt‑optimization tasks.
arXiv:2607. 21971v1 Announce Type: new Abstract: Test-time scaling through iterative self-evolution with environment feedback, as demonstrated by AlphaEvolve, shows remarkable performance gains.
The paper introduces a self‑evolving harness framework where a frozen language‑model agent first solves tasks and then edits its own harness based on run records. Using a 49‑line seed harness, the evolved harness improves average scores on in‑distribution benchmarks by 4.48 points and on out‑of‑distribution benchmarks by 12.64 points, surpassing Codex on the former and matching it on the latter. Continued evolution on a specific out‑of‑distribution benchmark further raises performance, and the study analyzes emergent mechanisms such as output truncation and history compaction.
arXiv:2504. 13822v3 Announce Type: replace-cross Abstract: The emergence of large pre-trained networks has revolutionized the AI field, unlocking new possibilities and achieving unprecedented performance.
arXiv:2608. 00316v1 Announce Type: new Abstract: Bayesian optimization (BO) has become the standard tool for sample-efficient optimization and owes its efficiency to uncertainty-aware search driven by generic statistical priors.
The paper introduces MEMENTO, a memory‑enhanced neural solver that improves routing problem solutions by using online data from repeated attempts to adjust action distributions during inference. It targets NP‑hard routing tasks such as the Traveling Salesman and Capacitated Vehicle Routing problems, outperforming existing tree‑search and policy‑gradient fine‑tuning methods. MEMENTO demonstrates strong scalability and data efficiency, achieving state‑of‑the‑art results on 11 of 12 evaluated tasks and enabling zero‑shot integration with diversity‑based solvers.
arXiv:2501. 17377v4 Announce Type: replace-cross Abstract: Deep Reinforcement Learning (DRL) has emerged as a promising approach for solving Combinatorial Optimization (CO) problems, such as the 3D Bin Packing Problem (3D-BPP), Traveling Salesman Problem (TSP), or Vehicle Routing Problem (VRP), but these neural solvers often exhibit brittleness when facing distribution shifts.
Contrastive Branch Policy Optimization (CBPO) is a reinforcement learning method that separates the allocation of a fixed rollout budget from the translation of branch outcomes into token-level credit. It uses generation entropy to screen branch positions, path- and node-level decay to distribute the budget, and Contrastive Branch Value (CBV) to estimate local decision sensitivity without changing reward signs. CBPO partitions trajectories into non-overlapping credit segments, preventing duplicated gradients and enabling fine-grained credit assignment using only outcome rewards.