DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning

• URL: http://arxiv.org/abs/2607.00341v1
• Date: Wed, 01 Jul 2026 02:32:02 GMT
• Title: DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning
• Abstract summary: Large language models achieve strong performance on many reasoning tasks when allowed to externalize intermediate steps as Chain-of-Thought (CoT)<n>We study this challenge through two-hop reasoning, a representative task where the model must compose multiple pieces of knowledge within a single forward pass.<n>We propose DiscoLoop, a looping architecture whose recurrence carries both a discrete embedding channel and a continuous hidden-state channel.
• Score: 91.94042219655866
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models achieve strong performance on many reasoning tasks when allowed to externalize intermediate steps as Chain-of-Thought (CoT). However, many questions require the model to internalize the multi-step reasoning within a single forward pass before generating the answer. We study this challenge through two-hop reasoning, a representative task where the model must compose multiple pieces of parametric knowledge within a single forward pass. Standard non-recurrent Transformers suffer from a depth-local storage problem: facts learned in earlier layers are unavailable where second-hop retrieval happens. We found that Looped Transformers mitigate this issue by reusing the same memory, but still generalize imperfectly. We show that the remaining bottleneck is representational. In the two-hop reasoning task, the first loop often makes the correct bridge entity nearly perfectly decodable, yet the corresponding hidden state remains poorly aligned with the bridge token embedding. Surprisingly, an easy training-free realignment intervention nearly closes the generalization gap. Building upon this insight, we propose DiscoLoop, a looping architecture whose recurrence carries both a discrete embedding channel and a continuous hidden-state channel. DiscoLoop achieves near-perfect accuracy with substantially fewer training steps across symbolic and synthetic-language multi-hop reasoning tasks. When applied to real-world pretraining, DiscoLoop attains lower training loss and stronger benchmark performance than looped-transformer baselines, suggesting that the mixed-channel design transfers to practical language modeling.

Related papers

• Why Knowing Both Hops Is Not Enough: Understanding Two-Hop Generalization in Language Models [34.21928044036961]
  Large language models (LLMs) can solve complex multi-hop problems yet exhibit puzzling failures on simple two-hop queries.<n>We show that LLMs generalize reliably when the second hop follows the training distribution, but always fail when it deviates.<n>We propose a recurrent-style training strategy, which enables transformers to reuse their reasoning circuitry across input forms.
  arXiv  Detail & Related papers  (2026-08-07T14:17:34Z)
• Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation [26.17880287280065]
  pyrag is a framework that reformulates multi-hop RAG as program synthesis and execution.<n>pyrag consistently outperforms strong baselines under both training-free and RL-trained settings.
  arXiv  Detail & Related papers  (2026-05-13T04:14:13Z)
• Thinking Deeper, Not Longer: Depth-Recurrent Transformers for Compositional Generalization [1.5736899098702974]
  We propose a depth-recurrent Transformer that decouples computational depth from parameter count.<n>Our architecture incorporates three mechanisms to make deep recurrence (20+ steps) stable.<n>We observe a clear emphcomputational frontier, where performance transitions from chance to near-perfect as thinking steps scale with task complexity.
  arXiv  Detail & Related papers  (2026-03-23T08:06:45Z)
• Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching [66.39914384073145]
  We propose a self-consistency framework that turns cheap diffusion-sampled reasoning into a reusable pool of step-level candidates.<n>We find that step-level recombination is most beneficial on harder problems.<n>Our training-free framework improves average accuracy by up to 2 across six math and coding tasks.
  arXiv  Detail & Related papers  (2026-02-26T11:08:39Z)
• Latent Chain-of-Thought? Decoding the Depth-Recurrent Transformer [0.8738725605667471]
  Chain-of-thought (CoT) reasoning has enabled transformer-based language models to excel at complex mathematics and multi-step planning.<n>In standard decoder-only architectures, these reasoning steps are externalized in natural language, improving interpretability at the cost of efficiency.<n>We investigate whether such reasoning structures emerge in Huginn-3.5B, a depth-recurrent Transformer that reuses layers at inference time without increasing parameter count.
  arXiv  Detail & Related papers  (2025-07-02T23:35:21Z)
• Reasoning with Latent Thoughts: On the Power of Looped Transformers [52.84192961524481]
  We show that for many synthetic reasoning problems, a $k$-layer transformer looped $L$ times nearly matches the performance of a $kL$-layer non-looped model.<n>Our empirical analysis reveals an intriguing phenomenon: looped and non-looped models exhibit scaling behavior that depends on their effective depth.
  arXiv  Detail & Related papers  (2025-02-24T18:49:05Z)
• How Do LLMs Perform Two-Hop Reasoning in Context? [76.79936191530784]
  Two-hop reasoning refers to the process of inferring a conclusion by making two logical steps.<n>Despite recent progress in large language models (LLMs), we surprisingly find that they can fail at solving simple two-hop reasoning problems.<n>We train a 3-layer Transformer from scratch on a synthetic two-hop reasoning task and reverse-engineer its internal information flow.
  arXiv  Detail & Related papers  (2025-02-19T17:46:30Z)
• Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering [71.49131159045811]
  Multi-hop reasoning requires aggregating multiple documents to answer a complex question. Existing methods usually decompose the multi-hop question into simpler single-hop questions. We propose an interpretable stepwise reasoning framework to incorporate both single-hop supporting sentence identification and single-hop question generation.
  arXiv  Detail & Related papers  (2022-08-22T13:24:25Z)
• Modeling Multi-hop Question Answering as Single Sequence Prediction [88.72621430714985]
  We propose a simple generative approach (PathFid) that extends the task beyond just answer generation. PathFid explicitly models the reasoning process to resolve the answer for multi-hop questions. Our experiments demonstrate that PathFid leads to strong performance gains on two multi-hop QA datasets.
  arXiv  Detail & Related papers  (2022-05-18T21:57:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.