arXiv AI
S-AI-Recursive: Convergent Recursive Reasoning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 26
Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses
The paper introduces Recuris, a recursive Experiential‑Working Memory architecture that lets long‑horizon agents track task progress and select skills based on current needs rather than full history. By coupling working memory with experiential memory, execution becomes structured evidence that localizes failures to specific memory components, enabling a bounded recursive memory‑evolution loop. Across four benchmarks and ten models, Recuris improves task success in 35 of 37 model‑benchmark pairs, raising state‑of‑the‑art performance on tau‑bench and SkillFlow and reducing common long‑horizon failures by up to 80%.
Hugging Face Trending Papers
Aug 25
Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses
Recursive self-improvement (RSI) remains hard in long-horizon tasks, where growing histories obscure the task state and misalign skill invocation. We introduce Recuris, a recursive Experiential-Workin...
arXiv Machine Learning
5d ago
Dissecting Hierarchical Reasoning Models: A Mechanistic Study
The paper investigates Hierarchical Reasoning Models (HRM), a class of hierarchical Transformer-based latent reasoning models, across Sudoku, Maze, and ARC-AGI-2 tasks. By comparing HRM to Transformer baselines, applying causal interventions on recurrent states, and conducting linear probe and sparse autoencoder ablations, the authors find that recurrent models outperform one-pass baselines, that high- and low-level states contribute differently across tasks, and that ablations of sparse autoencoder features cause larger behavioral changes than probe-direction ablations. The study concludes that HRM implements constraint‑aware iterative refinement on a puzzle‑specific solution state, with component contributions varying without a compact, causally important feature set.
arXiv AI
Jun 24
Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning
arXiv:2606. 24064v1 Announce Type: new Abstract: Distilling reasoning capabilities from strong to weak language models typically involves imitating specific solution trajectories, effectively transferring what to answer rather than how to reason.
arXiv AI
Sep 10
Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks
The paper introduces Feedback‑Enriched Environments (FEEs) as a new approach to training large language models as autonomous agents for long‑horizon tasks. By shifting from action guidance to observation enrichment during later stages of exploration, FEEs improve performance across SciWorld and BFCL benchmarks with various Qwen3 model scales and RL algorithms. The study shows that FEEs stabilize training, promote proactive exploration, embed environmental guidance into policy weights, and highlight intra‑group feedback consistency as key for stable optimization.
arXiv AI
Jul 2
AutoMem: Automated Learning of Memory as a Cognitive Skill
arXiv:2607. 01224v1 Announce Type: new Abstract: Memory expertise is a learned skill: knowing what to encode, when to retrieve, and how to organize knowledge--a capacity known in cognitive science as metamemory.