| Today at a glance |
|
1
s
|
2
New papers
|
3
Categories
|
|
|
AI for Optimization
0 new papers | 0 | 80 total analyzed
|
| No new papers this period. |
Automated Algorithm Discovery
1 new papers | 1 | 142 total analyzed
|
|
2026-05-21 | MIT, Sakana AI, Improbable AI Lab, MIT-IBM Computing Research Lab | 2605.22817
Bahlous-Boldi et al. introduce Vector Policy Optimization (VPO), an RL post-training method that trains LLMs to generate diverse candidate sets by combining multi-answer autoregressive generation with stochastic reward scalarization. The results are rigorously backed by empirical data, demonstrating that VPO continuously scales with test-time compute and successfully solves hard LiveCodeBench problems inside an AlphaEvolve-style evolutionary loop where standard GRPO completely stalls. The key insight is that collapsing vector rewards (such as per-test-case correctness) into a single scalar during RL causes mode collapse; instead, sampling random weightings from a Dirichlet distribution forces the policy to maintain a Pareto-diverse set of strategies. This is a fundamental advance for LLM evolutionary search, as applying VPO to mutator or generator models directly addresses sample efficiency and prevents premature convergence in automated algorithm design.
|
Optimizing AI Systems
1 new papers | 0 | 130 total analyzed
|
|
2026-05-21 | MIT, Kensho Technologies, Ben-Gurion University | 2605.22705
Schmidt et al. introduce ToaST, a tokenization method that replaces greedy heuristics like BPE by formulating vocabulary selection as an Integer Program to minimize total token count. The results are rigorously backed by numbers, demonstrating an 11% compression improvement over BPE and significantly better downstream language model performance. The key insight is that formulating the selection problem over a root-to-leaf tree structure yields an exceptionally tight Linear Programming relaxation, allowing exact OR solvers to scale to massive AI infrastructure problems.
|