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

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.

Related

• Zipping the Thought: When and How Compressed Reasoning Data Works in LLM Post-Training
• TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning
• The Geometric Reasoner: Manifold-Informed Latent Foresight Search for Long-Context Reasoning
• MemoSight: Unifying Context Compression and Multi Token Prediction for Reasoning Acceleration
• Reasoning about Reasoning: BAPO Bounds on Chain-of-Thought Token Complexity in LLMs

Source: arXiv cs.AI | 2026-08-03