Bifrost: Steering Strategic Trajectories to Bridge Contextual Gaps for Self-Improving Agents

• URL: http://arxiv.org/abs/2602.05810v1
• Date: Thu, 05 Feb 2026 16:03:56 GMT
• Title: Bifrost: Steering Strategic Trajectories to Bridge Contextual Gaps for Self-Improving Agents
• Authors: Quan M. Tran, Zhuo Huang, Wenbin Zhang, Bo Han, Koji Yatani, Masashi Sugiyama, Tongliang Liu,
• Abstract summary: We propose BrIdge contextual gap FoR imprOvised trajectory STeering (Bifrost) as a training-free method for self-improvement.<n>Bifrost consistently outperforms existing trajectory reuse and finetuned self-improvement methods.
• Score: 102.21483770287985
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autonomous agents excel in self-improvement through reflection and iterative refinement, which reuse successful task trajectories as in-context examples to assist subsequent reasoning. However, shifting across tasks often introduces a context mismatch. Hence, existing approaches either discard the trajectories or manipulate them using heuristics, leading to a non-negligible fine-tuning cost or unguaranteed performance. To bridge this gap, we reveal a context-trajectory correlation, where shifts of context are highly parallel with shifts of trajectory. Based on this finding, we propose BrIdge contextual gap FoR imprOvised trajectory STeering (Bifrost), a training-free method that leverages context differences to precisely guide the adaptation of previously solved trajectories towards the target task, mitigating the misalignment caused by context shifts. Our trajectory adaptation is conducted at the representation level using agent hidden states, ensuring trajectory transformation accurately aligns with the target context in a shared space. Across diverse benchmarks, Bifrost consistently outperforms existing trajectory reuse and finetuned self-improvement methods, demonstrating that agents can effectively leverage past experiences despite substantial context shifts.

Related papers

• TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training [53.93696896939915]
  Training tool-use agents typically rely on Supervised Fine-Tuning (SFT) on successful trajectories and Reinforcement Learning (RL) on pass-rate-selected tasks.<n>We propose TopoCurate, an interaction-aware framework that projects multi-trial rollouts from the same task into a unified semantic quotient topology.<n>TopoCurate achieves consistent gains of 4.2% (SFT) and 6.9% (RL) over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-03-02T10:38:54Z)
• A Turn Toward Better Alignment: Few-Shot Generative Adaptation with Equivariant Feature Rotation [67.2019317630466]
  Few-shot image generation aims to effectively adapt a source generative model to a target domain using very few training images.<n>We propose Equivariant Feature Rotation (EFR), a novel adaptation strategy that aligns source and target domains at two complementary levels.<n>Our method significantly enhances the generative performance within the targeted domain.
  arXiv  Detail & Related papers  (2025-12-24T13:48:22Z)
• CAPE: Context-Aware Diffusion Policy Via Proximal Mode Expansion for Collision Avoidance [15.311155448797386]
  contexts-aware diffusion policy via Proximal mode Expansion (CAPE)<n>CAPE expands trajectory distribution modes with context-aware prior and guidance at inference.<n>We evaluate CAPE on diverse manipulation tasks in cluttered unseen simulated and real-world settings.
  arXiv  Detail & Related papers  (2025-11-27T21:53:09Z)
• FAST: Similarity-based Knowledge Transfer for Efficient Policy Learning [57.4737157531239]
  Transfer Learning offers the potential to accelerate learning by transferring knowledge across tasks.<n>It faces critical challenges such as negative transfer, domain adaptation and inefficiency in selecting solid source policies.<n>In this work we challenge the key issues in TL to improve knowledge transfer, agents performance across tasks and reduce computational costs.
  arXiv  Detail & Related papers  (2025-07-27T22:21:53Z)
• Contrast & Compress: Learning Lightweight Embeddings for Short Trajectories [11.6132604160666]
  We propose a novel framework for learning fixed-dimensional embeddings for short trajectories by leveraging a Transformer encoder.<n>We analyze the influence of Cosine and FFT-based similarity metrics within the contrastive learning paradigm.<n>Our empirical evaluation on the Argoverse 2 dataset demonstrates that embeddings shaped by Cosine similarity objectives yield superior clustering of trajectories.
  arXiv  Detail & Related papers  (2025-06-03T07:53:04Z)
• Efficient Data Representation for Motion Forecasting: A Scene-Specific Trajectory Set Approach [12.335528093380631]
  This study introduces a novel approach for generating scene-specific trajectory sets tailored to different contexts.<n>A deterministic goal sampling algorithm identifies relevant map regions, while our Recursive In-Distribution Subsampling (RIDS) method enhances trajectory plausibility.<n>Experiments on the Argoverse 2 dataset demonstrate that our method achieves up to a 10% improvement in Driving Area Compliance.
  arXiv  Detail & Related papers  (2024-07-30T11:06:39Z)
• Augmenting Safety-Critical Driving Scenarios while Preserving Similarity to Expert Trajectories [3.072340427031969]
  Trajectory augmentation serves as a means to mitigate distributional shift in imitation learning. We propose a method designed to maintain similarity with expert trajectory data.
  arXiv  Detail & Related papers  (2024-04-20T11:05:47Z)
• Recurrent Aligned Network for Generalized Pedestrian Trajectory Prediction [41.000755300574156]
  Pedestrian trajectory prediction is a crucial component in computer vision and robotics.<n>Previous studies have tried to tackle this problem by leveraging a portion of the trajectory data from the target domain to adapt the model.<n>We introduce a Recurrent Aligned Network(RAN) to minimize the domain gap through domain alignment.
  arXiv  Detail & Related papers  (2024-03-09T06:17:09Z)
• Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning [125.61772424068903]
  Vision-and-language navigation (VLN) asks an agent to follow a given language instruction to navigate through a real 3D environment. We present a model-agnostic training paradigm, called Progressive Perturbation-aware Contrastive Learning (PROPER) to enhance the generalization ability of existing VLN agents.
  arXiv  Detail & Related papers  (2024-03-09T02:34:13Z)
• Self-supervised Augmentation Consistency for Adapting Semantic Segmentation [56.91850268635183]
  We propose an approach to domain adaptation for semantic segmentation that is both practical and highly accurate. We employ standard data augmentation techniques $-$ photometric noise, flipping and scaling $-$ and ensure consistency of the semantic predictions. We achieve significant improvements of the state-of-the-art segmentation accuracy after adaptation, consistent both across different choices of the backbone architecture and adaptation scenarios.
  arXiv  Detail & Related papers  (2021-04-30T21:32:40Z)
• Language-guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning [66.9937776799536]
  The emerging vision-and-language navigation (VLN) problem aims at learning to navigate an agent to the target location in unseen photo-realistic environments. The main challenges of VLN arise mainly from two aspects: first, the agent needs to attend to the meaningful paragraphs of the language instruction corresponding to the dynamically-varying visual environments. We propose a cross-modal grounding module to equip the agent with a better ability to track the correspondence between the textual and visual modalities.
  arXiv  Detail & Related papers  (2020-11-22T09:13:46Z)

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.