ThinkReset: Learnable Intermediate Interface Construction for Bounded-Context Long-Horizon Reasoning

Researchers propose ThinkReset, a method that constructs reusable intermediate interfaces to improve long-horizon reasoning under bounded context windows, addressing redundancy, context overflow, and error anchoring. The approach, detailed in arXiv:2607.28642v1, consistently improves success rates across multiple benchmarks by optimizing post-reset continuation success.

arXiv:2607.28642v1 Announce Type: new Abstract: Long chain-of-thought reasoning improves performance on complex problems, but it also introduces redundancy accumulation, context overflow, and error anchoring. We argue that under bounded context windows, the core bottleneck is not trajectory compression or test-time control, but the absence of a reusable intermediate interface that can replace discarded history and support continued solving. We further identify a key failure mode of outcome-reward-driven long-chain reinforcement learning: when the model has not solved the task before the window is nearly exhausted, the final-answer reward encourages premature guessing rather than continued careful reasoning. We propose ThinkReset, a text-space instantiation of this view. ThinkReset explicitly constructs reusable intermediate interfaces through interface writeback and reset, and directly optimizes post-reset continuation success. Across multiple long-horizon reasoning benchmarks, this perspective consistently improves success rates under fixed context windows.