Answer-Distribution Trajectories: A Stochastic-Dynamics View of LLM Reasoning

• URL: http://arxiv.org/abs/2609.09030v1
• Date: Tue, 08 Sep 2026 16:58:40 GMT
• Title: Answer-Distribution Trajectories: A Stochastic-Dynamics View of LLM Reasoning
• Abstract summary: Chain-of-thought reasoning provides a structured computation between a model's input and final answer.<n> entropy profiles track how uncertainty evolves over the reasoning process but do not reveal which competing hypotheses account for that uncertainty.<n>We introduce answer-distribution trajectories, a representation that tracks the model's full predictive distribution over answers as reasoning unfolds.
• Score: 29.58875226713171
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Chain-of-thought reasoning provides a structured computation between a model's input and final answer. Yet it is often evaluated through endpoint accuracy, which ignores the path taken to reach that answer. An emerging line of work addresses this limitation using entropy profiles, which track how uncertainty evolves over the reasoning process but do not reveal which competing hypotheses account for that uncertainty. We introduce answer-distribution trajectories, a stochastic-dynamics-inspired representation that tracks the model's full predictive distribution over answers as reasoning unfolds. As a strictly finer representation than endpoint and entropy summaries, answer-distribution trajectories enable us to characterize a trace through a dynamical reasoning profile spanning exploration, revision, motion, and commitment, and to distinguish different dynamical mechanisms of reasoning success and failure. Across sixteen open-weight language models and four reasoning benchmarks, we show that traces with the same endpoint and similar entropy profiles can exhibit substantially different reasoning dynamics. We further find substantial variation in these dynamics both within and across models and tasks, with different objectives favoring different dynamical profiles. Additionally, we show that training and inference choices systematically reshape these profiles. Our results suggest that answer-distribution trajectories provide a rich framework for analysing and evaluating the dynamics of LLM reasoning.

Related papers

• Learning Structured Reasoning via Tractable Trajectory Control [99.75278337895024]
  Ctrl-R is a framework for learning structured reasoning via tractable trajectory control.<n>We show that Ctrl-R enables effective exploration and internalization of previously unattainable reasoning patterns.
  arXiv  Detail & Related papers  (2026-03-02T09:18:19Z)
• Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure [58.89643769707751]
  We study latent chain-of-thought as a manipulable causal process in representation space.<n>We find that latent-step budgets behave less like homogeneous extra depth and more like staged functionality with non-local routing.<n>These results motivate mode-conditional and stability-aware analyses as more reliable tools for interpreting and improving latent reasoning systems.
  arXiv  Detail & Related papers  (2026-02-09T15:25:12Z)
• Interpreting and Controlling LLM Reasoning through Integrated Policy Gradient [27.26870804635122]
  Large language models (LLMs) demonstrate strong reasoning abilities in solving complex real-world problems.<n> internal mechanisms driving these complex reasoning behaviors remain opaque.<n>We propose Integrated Policy Gradient (IPG), a novel framework that attributes reasoning behaviors to model's inner components.
  arXiv  Detail & Related papers  (2026-02-02T16:43:09Z)
• Reasoning as State Transition: A Representational Analysis of Reasoning Evolution in Large Language Models [50.39102836928242]
  We introduce a representational perspective to investigate the dynamics of the model's internal states.<n>We discover that post-training yields only limited improvement in static initial representation quality.
  arXiv  Detail & Related papers  (2026-01-31T15:23:33Z)
• Analyzing Reasoning Consistency in Large Multimodal Models under Cross-Modal Conflicts [74.47786985522762]
  We identify a critical failure mode termed textual inertia, where models tend to blindly adhere to the erroneous text while neglecting conflicting visual evidence.<n>We propose the LogicGraph Perturbation Protocol that structurally injects perturbations into the reasoning chains of diverse LMMs.<n>Results reveal that models successfully self-correct in less than 10% of cases and predominantly succumb to blind textual error propagation.
  arXiv  Detail & Related papers  (2026-01-07T16:39:34Z)
• Variational Reasoning for Language Models [93.08197299751197]
  We introduce a variational reasoning framework for language models that treats thinking traces as latent variables.<n>We show that rejection sampling finetuning and binary-reward RL, including GRPO, can be interpreted as local forward-KL objectives.
  arXiv  Detail & Related papers  (2025-09-26T17:58:10Z)
• CTRLS: Chain-of-Thought Reasoning via Latent State-Transition [57.51370433303236]
  Chain-of-thought (CoT) reasoning enables large language models to break down complex problems into interpretable intermediate steps.<n>We introduce groundingS, a framework that formulates CoT reasoning as a Markov decision process (MDP) with latent state transitions.<n>We show improvements in reasoning accuracy, diversity, and exploration efficiency across benchmark reasoning tasks.
  arXiv  Detail & Related papers  (2025-07-10T21:32:18Z)
• Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning [9.795934690403374]
  It is still unclear which multi-step reasoning mechanisms are used by language models to solve such tasks.<n>We employ circuit analysis and self-influence functions to evaluate the changing importance of each token throughout the reasoning process.<n>We demonstrate that the underlying circuits reveal a human-interpretable reasoning process used by the model.
  arXiv  Detail & Related papers  (2025-02-13T07:19:05Z)
• On the Reasoning Capacity of AI Models and How to Quantify It [0.0]
  Large Language Models (LLMs) have intensified the debate surrounding the fundamental nature of their reasoning capabilities.<n>While achieving high performance on benchmarks such as GPQA and MMLU, these models exhibit limitations in more complex reasoning tasks.<n>We propose a novel phenomenological approach that goes beyond traditional accuracy metrics to probe the underlying mechanisms of model behavior.
  arXiv  Detail & Related papers  (2025-01-23T16:58:18Z)
• Identifiable Representation and Model Learning for Latent Dynamic Systems [0.0]
  We study the problem of identifiable representation and model learning for latent dynamic systems.<n>We prove that, for linear and affine nonlinear latent dynamic systems with sparse input matrices, it is possible to identify the latent variables up to scaling.
  arXiv  Detail & Related papers  (2024-10-23T13:55:42Z)
• Geometric Analysis of Reasoning Trajectories: A Phase Space Approach to Understanding Valid and Invalid Multi-Hop Reasoning in LLMs [0.0]
  This paper proposes a novel approach to analyzing multi-hop reasoning in language models through Hamiltonian mechanics.<n>We map reasoning chains in embedding spaces to Hamiltonian systems, defining a function that balances reasoning progression (kinetic energy) against question relevance (potential energy)
  arXiv  Detail & Related papers  (2024-10-06T09:09:14Z)
• Understanding Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation [110.71955853831707]
  We view LMs as deriving new conclusions by aggregating indirect reasoning paths seen at pre-training time. We formalize the reasoning paths as random walk paths on the knowledge/reasoning graphs. Experiments and analysis on multiple KG and CoT datasets reveal the effect of training on random walk paths.
  arXiv  Detail & Related papers  (2024-02-05T18:25:51Z)
• Learning Interacting Dynamical Systems with Latent Gaussian Process ODEs [13.436770170612295]
  We study for the first time uncertainty-aware modeling of continuous-time dynamics of interacting objects. Our model infers both independent dynamics and their interactions with reliable uncertainty estimates.
  arXiv  Detail & Related papers  (2022-05-24T08:36:25Z)

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.