The paper investigates why reinforcement learning with verifiable rewards (RLVR) reduces the diversity of solutions in reasoning tasks. By analyzing the Countdown task, the authors show that RLVR contracts the solution space mainly at the entrance—before the first arithmetic operation—causing a 67% drop in solution coverage. They demonstrate that providing an unselected entrance prefix or applying entrance‑targeted interventions can restore or even improve coverage without harming accuracy.
By Qiancheng Zhou, Ruizhe Li
arXiv:2608. 06762v1 Announce Type: new Abstract: Bisimulation metrics quantify behavioral similarity in Markov decision processes, but their Wasserstein fixed-point operator updates every state pair and incurs quadratic pairwise work.
By Ibne Farabi Shihab, Joyanta Jyoti Mondal
arXiv:2608. 12959v1 Announce Type: cross Abstract: Latent world models are judged by how well they predict, so when planning fails at long horizons the natural reading is that the predictor degrades.
By Joyjeet Singh
arXiv:2609.38349v1 Announce Type: cross
Abstract: Modern agentic systems combine an AI model with a harness that controls execution and environmental interactions. Harness design strongly affects lon...
By Prithwish Jana, Mononito Goswami, Hao Liu, Xinyu Li, Langlin Huang, Zhehui Huang, Zhishen Huang, Patrick Bl\"obaum, Anoop Deoras, Purak Jain, Nikos Kanakaris, Sahika Genc
The paper introduces Reinforcement Learning with Decomposed Subtasks (RLDS), a method that splits trajectory rewards into per‑subtask shares before policy updates, replacing the scalar advantage used in Group Relative Policy Optimization (GRPO). RLDS employs Subtask‑Decomposed Advantage Estimation (SDAE) to compute group‑relative advantages and distribute credit to tokens based on subtask importance, focusing on steps where a reflection marks a subtask as consequential. Experiments on four benchmarks—FrozenLake, HotpotQA, ScienceWorld, and DeepResearch—show that RLDS improves performance on high‑heterogeneity tasks (ScienceWorld and FrozenLake) and is more compute‑efficient than scalar GRPO for long rollouts.
By Mattie Terzolo, Mikolaj Sacha, Ayan Sinha, Andrew Rabinovich
arXiv:2509. 08521v2 Announce Type: replace-cross Abstract: FMT$^{*}$ plans efficiently in static worlds by expanding a cost-ordered wavefront and collision-checking lazily, but its single-pass unvisited rule cannot revise paths when obstacles change.
By Soheil Espahbodi Nia
arXiv:2608. 11318v1 Announce Type: cross Abstract: Many sequential construction tasks exhibit exact symmetry at completion while their execution remains directed and history-dependent.
By Yi Liu
The paper reports on a large‑scale verified search experiment using a 30B language model on a laptop, evaluating three operator packages—schematic notebooks, named obstacles, and behavioural repulsion—in a factorial design across nine construction problems. Results show that the full composition of operators closes the seed‑to‑record gap more effectively than any single component, increases construction‑hash diversity, and that memory plus repulsion consistently avoids collapse. A frontier proposer achieves similar gains in far fewer samples, but the search ultimately stalls near a plateau where the reference family is adopted and optimized only when provided as code.
By Roberto I. Ono Filho
arXiv:2608.27757v1 Announce Type: new
Abstract: Searchless chess networks reach human master strength from a single forward pass by imitating a stronger teacher: the strongest, Leela Chess Zero's (Lc...
By Szymon Mi{\l}osz, Piotr Duch, Szymon Grabowski
ARC‑Bench is a new benchmark that tests whether frozen JEPA‑style latent world models can correctly rank candidate actions by latent distance. The study finds that the assumption of latent rankability fails dramatically in both navigation and manipulation tasks, with the top‑scored actions often being suboptimal. Closed‑loop replanning masks this defect, but reducing replanning frequency reveals the underlying ranking failures.
By Zhengshu Zhang, Zhiyuan Li
arXiv:2605. 01928v2 Announce Type: replace Abstract: We optimize losses that jump: spiking thresholds, quantized layers, and discrete routing put jumps in the forward pass, where backpropagation does not apply.
By An T. Le
arXiv:2608.30427v1 Announce Type: cross
Abstract: Speculative decoding speeds up generation with an efficient draft model (drafter) that proposes tokens for a target model to verify in one pass, pres...
By Ephrem Wu