mlsanityData to 14 Oct 2026

CB-Agent: Concept-Based In-Context Learning for Sequential Action Selection

arXiv 2610.14574 ↗First posted 10 Oct 2026cs.AI cs.LGcited by 0

On the map: LLM agents and tool use → Reinforcement learning for LLM agents also fits: Multimodal and embodied agents

Abstract (arXiv)

In-context learning (ICL) allows large language models to use demonstrations without updating their parameters. For interactive agents, demonstrations are trajectories of reasoning, actions, and observations that illustrate how to complete a task. Reusing demonstrations in new situations is challenging: directly inputting full trajectories consumes limited prompt space and constrains the overall effectiveness, while natural-language summaries require the agent to translate general guidance into specific action choices. Therefore, we study whether expert action choices can directly supervise a reusable scoring rule. We propose CB-Agent, which extends concept-based ICL to sequential action selection. We extract environment-action decisions from expert trajectories and fit a concept vector by maximum likelihood to model the conditional distribution over candidate actions given the context. This model combines the concept with frozen language-model features and priors. During ReAct interaction, the agent uses this distribution to select environment actions without including demonstrations in the action-scoring context. Across TextWorld, ALFWorld, and ScienceWorld, CB-Agent achieves the highest cross-benchmark average among the evaluated methods at all three tested model sizes and ranks first on TextWorld and ScienceWorld at each size. ALFWorld experiments support the learned concept's contribution beyond prior-only scoring and show further gains when combined with Reflexion. Code is available at https://anonymous.4open.science/r/CB-Agent-DFF9/.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use. Builds on 28 of its 31 references that are in the map. First posted on arXiv 10 Oct 2026.

Builds on

28 of 31 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Voyager: An Open-Ended Embodied Agent with Large Language Models25 May
  2. 2023Reflexion: Language Agents with Verbal Reinforcement Learning20 Mar

Other references · 26

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  6. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  7. 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,475
  8. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,205
  9. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
  10. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,135
  11. 2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 938
  12. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 876
14 more
  1. 2021Learning To Retrieve Prompts for In-Context Learningcited by 648
  2. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMscited by 338
  3. 2022ScienceWorld: Is your Agent Smarter than a 5th Grader?cited by 327
  4. 2023In-Context Learning Creates Task Vectorscited by 312
  5. 2018TextWorld: A Learning Environment for Text-based Gamescited by 310
  6. 2023Function Vectors in Large Language Modelscited by 308
  7. 2023AdaPlanner: Adaptive Planning from Feedback with Language Modelscited by 196
  8. 2024Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Modelscited by 100
  9. 2024Agent Planning with World Knowledge Modelcited by 70
  10. 2025ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflectioncited by 31
  11. 2024StateAct: Enhancing LLM Base Agents via Self-prompting and State-trackingcited by 23
  12. 2019On Universal Features for High-Dimensional Learning and Inferencecited by 20
  13. 2025On Theoretical Interpretations of Concept-Based In-Context Learningcited by 3
  14. 2026DELTAMEM: Incremental Experience Memory for LLM Agents via Residual Treescited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Leveraging In-Context Learning for Language Model Agents
  2. 2025DICE: Dynamic In-Context Example Selection in LLM Agents via Efficient Knowledge Transfer
  3. 2024ReAct Meets ActRe: When Language Agents Enjoy Training Data Autonomy
  4. 2024VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of Thought
  5. 2026ActICL: Post-Training for Agentic Multimodal In-Context Learning
  6. 2025Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks
  7. 2026V-ICAL Bench: Evaluating Video In-Context Learning for Multimodal Agents in Interactive Environments
  8. 2025Learning from Online Videos at Inference Time for Computer-Use Agents