From Final Artifacts to Trajectories: Retrospective Process Supervision for Evidence-Grounded Long-Form Generation

• URL: http://arxiv.org/abs/2608.30461v1
• Date: Mon, 31 Aug 2026 08:47:39 GMT
• Title: From Final Artifacts to Trajectories: Retrospective Process Supervision for Evidence-Grounded Long-Form Generation
• Abstract summary: RetroGen is a self-improving framework for retrospective process supervision.<n>It reconstructs latent trajectories from expert artifacts, verifies them against the artifact and supporting evidence, and trains models on their own successful reconstruction data.<n>Experiments show that RetroGen improves grounding, faithful synthesis, and long-form evidence-seeking agent tasks.
• Score: 49.496216822640974
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Trajectory data is getting more vital for training large language models for boosting the agentic abilities. Unlike the verifiable domains such as coding or mathematics, scaling trajectory data for open-ended tasks is much more difficult because these tasks lack singular ground truth and are costly to annotate or verify. In this paper, we propose RetroGen, a self-improving framework of retrospective process supervision. Our key observation is that although expert trajectories are scarce, high-quality final artifacts such as literature reviews, analyst reports and legal judgments, are abundant in pre-training data and can be viewed as compressed traces of the evidence-seeking processes that produced them. RetroGen reconstructs candidate latent trajectories from expert artifacts, verifies them against both the artifact and supporting evidence, and trains models on their own successful reconstruction data, without requiring trajectory data from stronger models. Experiments show that RetroGen improves grounding, faithful synthesis, and long-form evidence-seeking agent tasks.

Related papers

• GRACE: Graph-Grounded Reflective Agent Copilot Engine for Expert-in-the-Loop Knowledge Expansion [2.729876880765472]
  Large language models frequently generate plausible but ungrounded claims.<n>We introduce GRACE, a framework that deconstructs responses into atomic claims and grounds them against trusted knowledge priors.<n>We evaluate GRACE across multiple language models and on datasets spanning both general and domain-specific knowledge.
  arXiv  Detail & Related papers  (2026-09-03T20:03:20Z)
• Copy Less, Ground More: Overcoming Repetitive Copying in Long-Context Reasoning via Evidence-Aware Reinforcement Learning [42.17614767170884]
  We show that models extensively copy text from the input into their reasoning traces rather than productively solving the problem.<n>By separating each prompt into task-relevant key evidence and irrelevant distractor context, we show that the root cause is insufficient grounding.<n>Motivated by this diagnosis, we propose GEAR, a reward shaping method that augments the accuracy signal with a grounding reward for overlap with key evidence and a distractor penalty for overlap with irrelevant context.
  arXiv  Detail & Related papers  (2026-07-21T17:59:21Z)
• AgentTrails: Towards Trust and Reuse for Agentic Tasks [12.615897924172812]
  LLM-powered agents tackle complex tasks by invoking tools, querying databases, executing code, and manipulating intermediate artifacts.<n>These agents follow trajectories that are typically stored as chronological logs, obscuring the underlying dataflow.<n>We present AgentTrails, a prototype system for agent provenance and sensemaking.
  arXiv  Detail & Related papers  (2026-07-21T07:53:58Z)
• Experience Graphs: The Data Foundation for Self-Improving Agents [24.60392207371798]
  We argue that long-horizon agentic tasks -- code generation, scientific discovery, design -- are such a workload.<n>This search produces a structured object we call an experience graph.<n>We propose Trellis: a data foundation that treats the experience graph as first-class, governed, queryable database.
  arXiv  Detail & Related papers  (2026-06-29T06:02:20Z)
• Understanding by Reconstruction: Reversing the Software Development Process for LLM Pretraining [66.89012795621349]
  Large Language Models (LLMs) often struggle with the deep, long-horizon reasoning required for complex software engineering.<n>We propose a novel paradigm: understanding via reconstruction.<n>We introduce a framework that synthesizes latent agentic trajectories using a multi-agent simulation.
  arXiv  Detail & Related papers  (2026-03-11T09:23:20Z)
• Large Language Models as Realistic Microservice Trace Generators [48.730974361862366]
  This paper proposes a first-of-a-kind approach that relies on training a large language model (LLM) to generate synthetic workload traces.<n>We show that TraceLLM produces diverse, realistic traces under varied conditions, outperforming existing approaches in both accuracy and validity.<n>TraceLLM adapts to downstream trace-related tasks, such as predicting key trace features and infilling missing data.
  arXiv  Detail & Related papers  (2024-12-16T12:48:04Z)
• Transcendence: Generative Models Can Outperform The Experts That Train Them [55.885802048647655]
  We study the phenomenon of transcendence: when a generative model achieves capabilities that surpass the abilities of the experts generating its data. We demonstrate transcendence by training an autoregressive transformer to play chess from game transcripts, and show that the trained model can sometimes achieve better performance than all players in the dataset.
  arXiv  Detail & Related papers  (2024-06-17T17:00:52Z)
• Data-Independent Operator: A Training-Free Artifact Representation Extractor for Generalizable Deepfake Detection [105.9932053078449]
  In this work, we show that, on the contrary, the small and training-free filter is sufficient to capture more general artifact representations. Due to its unbias towards both the training and test sources, we define it as Data-Independent Operator (DIO) to achieve appealing improvements on unseen sources. Our detector achieves a remarkable improvement of $13.3%$, establishing a new state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-03-11T15:22:28Z)
• Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy [164.83371924650294]
  We show that strong performance can be achieved by a method we call Iter-RetGen, which synergizes retrieval and generation in an iterative manner. A model output shows what might be needed to finish a task, and thus provides an informative context for retrieving more relevant knowledge. Iter-RetGen processes all retrieved knowledge as a whole and largely preserves the flexibility in generation without structural constraints.
  arXiv  Detail & Related papers  (2023-05-24T16:17:36Z)
• Adversarial Imitation Learning with Trajectorial Augmentation and Correction [61.924411952657756]
  We introduce a novel augmentation method which preserves the success of the augmented trajectories. We develop an adversarial data augmented imitation architecture to train an imitation agent using synthetic experts. Experiments show that our data augmentation strategy can improve accuracy and convergence time of adversarial imitation.
  arXiv  Detail & Related papers  (2021-03-25T14:49:32Z)

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.