Forecasting Future Behavior as a Learning Task

• URL: http://arxiv.org/abs/2606.11445v1
• Date: Tue, 09 Jun 2026 20:56:23 GMT
• Title: Forecasting Future Behavior as a Learning Task
• Abstract summary: We train Behavior Forecasters that operate on a single reasoning trajectory to make the same forecasts one would typically seek from an explanation.<n>We evaluate this approach on two tasks: how likely the LRM is to repeat its answer on re-runs, and how removing parts of the input changes its answer.
• Score: 25.073460373115733
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Trust in an AI system is often anchored by explanations of how it works, which one then uses to forecast its behavior on new inputs. For large reasoning models (LRMs), this conventional route is particularly difficult to follow: explanation methods for single token generations do not naturally generalize to long trajectories, and the trajectories themselves are often not faithful when read as natural language. We propose an alternative that bypasses the explanation step: treat behavior forecasting as a learnable task and train Behavior Forecasters that operates on a single reasoning trajectory to make the same forecasts one would typically seek from an explanation. The forecaster's training data is obtained by querying the LRM with no human annotation, and its inference is done in a single forward pass. We instantiate this approach on two tasks: how likely the LRM is to repeat its answer on re-runs, and how removing parts of the input changes its answer. We evaluate this approach on both tasks across three diverse reasoning datasets and find that trained Behavior Forecasters are more accurate than GPT-5.4 and Claude Opus-4.6 reading the same trajectories as naive readers, at a small fraction of their inference cost. We find that fine-tuning the backbone end-to-end and initializing it from the target LRM are each necessary for strong performance. These results show that the reasoning trajectory carries information about the LRM's future behavior that goes beyond what naive reading conveys.

Related papers

• Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision [49.12474373883331]
  We show that LMs trained on fixed counterfactual explanations produce explanations more faithful to their own current behaviors than to those of their training targets.<n>This "introspective" coupling occurs when training explanations remain sufficiently correlated with current behaviors over the course of training.<n>We also show that introspective coupling tracks behavior shifts: when explanation training is provided concurrently with other post-training objectives, explanations track those shifts without requiring updated supervision.
  arXiv  Detail & Related papers  (2026-06-30T17:59:32Z)
• Predicting Future Behaviors in Reasoning Models Enables Better Steering [35.89008737242842]
  Test-time steering controls large reasoning models (LRMs) by intervening on their hidden representations, but it can degrade output quality.<n>We argue that prior steering work implicitly relies on internal features that detect behavior in already generated text.<n>We train activation probes to predict future behavior likelihoods from intermediate reasoning steps.<n>These probes predict the most likely behavior with 64%-91% accuracy, revealing a separate type of internal prediction features.
  arXiv  Detail & Related papers  (2026-06-09T17:49:24Z)
• Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics [42.27928681606673]
  Large Reasoning Models (LRMs) introduce new opportunities for safety monitoring through their Chain of Thought (CoT) reasoning.<n>We investigate the hidden representations of LRMs to determine whether future behavior can be predicted from prompt and CoT representations.<n>We find that future model behavior is more distinguishable when examined over the full trajectory than from a single static prediction.
  arXiv  Detail & Related papers  (2026-05-18T15:29:04Z)
• Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors [45.578570554635775]
  Large language models (LLMs) now solve multi-step problems by emitting extended chains of thought.<n>We study a simple mechanism that converts recurring reasoning fragments into concise, reusable "behaviors"<n>These behaviors are stored in a "behavior handbook" which supplies them to the model in-context at inference or distills them into parameters via supervised fine-tuning.
  arXiv  Detail & Related papers  (2025-09-16T16:44:26Z)
• CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models [29.95434387343843]
  We propose a unified framework that mitigates length bias through three components.<n>CoLD consistently reduces reward-length correlation, improves accuracy in step selection, and encourages more concise, logically valid reasoning.
  arXiv  Detail & Related papers  (2025-07-21T15:07:59Z)
• Improve Vision Language Model Chain-of-thought Reasoning [86.83335752119741]
  Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness. We show that training VLM on short answers does not generalize well to reasoning tasks that require more detailed responses.
  arXiv  Detail & Related papers  (2024-10-21T17:00:06Z)
• 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)
• You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction [52.442129609979794]
  Recent deep learning approaches for trajectory prediction show promising performance. It remains unclear which features such black-box models actually learn to use for making predictions. This paper proposes a procedure that quantifies the contributions of different cues to model performance.
  arXiv  Detail & Related papers  (2021-10-11T14:24:15Z)
• Injecting Knowledge in Data-driven Vehicle Trajectory Predictors [82.91398970736391]
  Vehicle trajectory prediction tasks have been commonly tackled from two perspectives: knowledge-driven or data-driven. In this paper, we propose to learn a "Realistic Residual Block" (RRB) which effectively connects these two perspectives. Our proposed method outputs realistic predictions by confining the residual range and taking into account its uncertainty.
  arXiv  Detail & Related papers  (2021-03-08T16:03:09Z)
• Value-driven Hindsight Modelling [68.658900923595]
  Value estimation is a critical component of the reinforcement learning (RL) paradigm. Model learning can make use of the rich transition structure present in sequences of observations, but this approach is usually not sensitive to the reward function. We develop an approach for representation learning in RL that sits in between these two extremes. This provides tractable prediction targets that are directly relevant for a task, and can thus accelerate learning the value function.
  arXiv  Detail & Related papers  (2020-02-19T18:10:20Z)

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.