arXiv:2604. 04721v3 Announce Type: replace Abstract: People often optimize for long-term goals in collaboration: A mentor or companion doesn't just answer questions, but also scaffolds learning, tracks progress, and prioritizes the other person's growth over immediate results.
The paper introduces a new reward, GRPO, that encourages large reasoning models (LRMs) to efficiently determine whether a task is solvable before generating a full chain of thought. Fine‑tuning 4B LRMs with this reward improves their ability to abstain from answering unanswerable prompts by an average of 12.8% while producing 44% shorter chains of thought. The approach also preserves the models’ overall answering performance.
arXiv:2607. 21306v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as tutors and thought partners, helping users reason through problems.
arXiv:2606. 01375v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly entering students' learning practices, but their educational value depends on whether they support reasoning or enable task completion without engagement.
arXiv:2602. 09924v4 Announce Type: replace-cross Abstract: Running LLMs with extended reasoning on every problem is expensive, but determining which inputs actually require additional compute remains challenging.
The paper investigates the limitations of post-training AI agents that can autonomously train large language models. It distinguishes between execution-level capability—making adjustments within a chosen training strategy—and strategy-level capability—revising the overall approach based on new evidence. Analysis of many public post-training runs shows that agents lock into a strategy early and then only perform local tweaks, regardless of task. Experiments with experience scaffolds, human guidance, and extra compute improve execution but do not enable strategy reevaluation, indicating that agents lack a mechanism to spontaneously reassess their strategy during training.
The paper argues that large language models need adaptive reasoning rather than fixed reasoning budgets. It shows that over‑reasoning leads to high computational cost without accuracy gains, while under‑reasoning results in incorrect or incomplete solutions. The authors evaluate these failure modes on MATH‑500 and the GAIA benchmark, highlighting the need for dynamic reasoning allocation in agentic AI systems.
arXiv:2607. 21856v1 Announce Type: new Abstract: Modern reasoning models depend on reasoning data, today sourced from human annotations or distilled from stronger LLMs.
arXiv:2609.37588v1 Announce Type: new Abstract: Users of language-based assistive agents often make ambiguous requests. In response, an assistant can either directly act on its interpretation of the...
arXiv:2605. 16283v3 Announce Type: replace-cross Abstract: Large-scale AI deployment data and controlled learning experiments characterize different consequences of the same technology.
The paper investigates how large language models (LLMs) balance capability and efficiency when using Chain-of-Thought reasoning on arithmetic and algorithmic tasks. It finds that while larger models solve more problems correctly, the improvement follows an exponential decay that slows with scale, indicating diminishing returns. Additionally, the length of reasoning output grows with problem size but does not improve with larger models, suggesting efficiency does not benefit from scaling.
Users of language-based assistive agents often make ambiguous requests. In response, an assistant can either directly act on its interpretation of the request --- risking misalignment with the user --...