CLEAR: Context Augmentation from Contrastive Learning of Experience via Agentic Reflection

• URL: http://arxiv.org/abs/2604.07487v1
• Date: Wed, 08 Apr 2026 18:26:59 GMT
• Title: CLEAR: Context Augmentation from Contrastive Learning of Experience via Agentic Reflection
• Abstract summary: We propose a generative context augmentation framework using Contrastive Learning of Experience via Agentic Reflection (CLEAR)<n>CLEAR first employs a reflection agent to perform contrastive analysis over past execution trajectories and summarize useful context for each observed task.<n>We further optimize CAM using reinforcement learning, where the reward signal is obtained by running the task execution agent.
• Score: 17.486111179784757
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large language model agents rely on effective model context to obtain task-relevant information for decision-making. Many existing context engineering approaches primarily rely on the context generated from the past experience and retrieval mechanisms that reuse these context. However, retrieved context from past tasks must be adapted by the execution agent to fit new situations, placing additional reasoning burden on the underlying LLM. To address this limitation, we propose a generative context augmentation framework using Contrastive Learning of Experience via Agentic Reflection (CLEAR). CLEAR first employs a reflection agent to perform contrastive analysis over past execution trajectories and summarize useful context for each observed task. These summaries are then used as supervised fine-tuning data to train a context augmentation model (CAM). Then we further optimize CAM using reinforcement learning, where the reward signal is obtained by running the task execution agent. By learning to generate task-specific knowledge rather than retrieve knowledge from the past, CAM produces context that is better tailored to the current task. We conduct comprehensive evaluations on the AppWorld and WebShop benchmarks. Experimental results show that CLEAR consistently outperforms strong baselines. It improves task completion rate from 72.62% to 81.15% on AppWorld test set and averaged reward from 0.68 to 0.74 on a subset of WebShop, compared with baseline agent. Our code is publicly available at https://github.com/awslabs/CLEAR.

Related papers

• Learning to Reason and Use Tools through Unsupervised Fine-Tuning in Task-Oriented Dialog Systems [4.740691414185166]
  We adapt the ReAct framework for Task-Oriented Dialogue, enabling Large Language Models to access external knowledge and produce factual responses.<n>We propose an unsupervised fine-tuning pipeline that harvests reasoning trajectories via in-context learning inference.<n> Experiments on the SIMMC dataset demonstrate that ReAct-based systems outperform baselines due to superior reasoning and tool use.
  arXiv  Detail & Related papers  (2026-08-31T08:22:26Z)
• Knowledge Reutilization in Meta-Reinforcement Learning [51.07319647819108]
  We propose a meta-knowledge reutilization framework that learns task-level knowledge on a dynamics-simplified agent and transfers it to heterogeneous agents.<n>We show that our framework reduces final-step tracking error by 94.75% -- 99.79% compared with recent state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-06-16T16:32:28Z)
• SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents [35.45207852488779]
  We introduce a Tool-Memory based self-evolving agentic framework SEARL.<n>Unlike approaches that directly utilize interaction experiences, our method constructs a structured experience memory that integrates planning with execution.<n>We evaluate our framework on knowledge reasoning and mathematics tasks, demonstrating its effectiveness in achieving more practical and efficient learning.
  arXiv  Detail & Related papers  (2026-04-09T04:38:47Z)
• Retrieval-Augmented LLM Agents: Learning to Learn from Experience [16.248836438253814]
  We study how to train retrieval-augmented LLM agents to leverage retrieved trajectories in-context.<n>We establish a robust supervised fine-tuning (SFT) recipe using LoRA that outperforms several state-of-the-art agent training pipelines.<n>Our results demonstrate that this combined approach significantly improves generalization to unseen tasks.
  arXiv  Detail & Related papers  (2026-03-18T20:45:04Z)
• ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization [86.57743637722596]
  Large Language Model (LLM)-based web agents demonstrate strong performance on knowledge-intensive tasks.<n>Complex queries involving multiple entities, intertwined relationships, and high uncertainty demand extensive search cycles.<n>We introduce ReSum, a novel paradigm that enables indefinite exploration through periodic context summarization.
  arXiv  Detail & Related papers  (2025-09-16T17:57:22Z)
• Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Models [51.608246558235166]
  SCARLet is a framework for training utility-based retrievers in RALMs.<n>It incorporates two key factors, multi-task generalization and inter-passage interaction.<n>We evaluate our approach on ten datasets across various tasks, both in-domain and out-of-domain.
  arXiv  Detail & Related papers  (2025-04-01T09:28:28Z)
• CoPS: Empowering LLM Agents with Provable Cross-Task Experience Sharing [70.25689961697523]
  We propose a generalizable algorithm that enhances sequential reasoning by cross-task experience sharing and selection. Our work bridges the gap between existing sequential reasoning paradigms and validates the effectiveness of leveraging cross-task experiences.
  arXiv  Detail & Related papers  (2024-10-22T03:59:53Z)
• P-RAG: Progressive Retrieval Augmented Generation For Planning on Embodied Everyday Task [94.08478298711789]
  Embodied Everyday Task is a popular task in the embodied AI community. Natural language instructions often lack explicit task planning. Extensive training is required to equip models with knowledge of the task environment.
  arXiv  Detail & Related papers  (2024-09-17T15:29:34Z)
• ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation [43.270424225285105]
  We focus on adapting and empowering a pure large language model for zero-shot and few-shot recommendation tasks. We propose Retrieval-enhanced Large Language models (ReLLa) for recommendation tasks in both zero-shot and few-shot settings.
  arXiv  Detail & Related papers  (2023-08-22T02:25:04Z)
• On Context Distribution Shift in Task Representation Learning for Offline Meta RL [7.8317653074640186]
  We focus on context-based OMRL, specifically on the challenge of learning task representation for OMRL. To overcome this problem, we present a hard-sampling-based strategy to train a robust task context encoder.
  arXiv  Detail & Related papers  (2023-04-01T16:21:55Z)
• Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels [112.63440666617494]
  Reinforcement learning algorithms can succeed but require large amounts of interactions between the agent and the environment. We propose a new method to solve it, using unsupervised model-based RL, for pre-training the agent. We show robust performance on the Real-Word RL benchmark, hinting at resiliency to environment perturbations during adaptation.
  arXiv  Detail & Related papers  (2022-09-24T14:22:29Z)
• Retrieval-Augmented Reinforcement Learning [63.32076191982944]
  We train a network to map a dataset of past experiences to optimal behavior. The retrieval process is trained to retrieve information from the dataset that may be useful in the current context. We show that retrieval-augmented R2D2 learns significantly faster than the baseline R2D2 agent and achieves higher scores.
  arXiv  Detail & Related papers  (2022-02-17T02:44:05Z)

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.