A Study on Leveraging Search and Self-Feedback for Agent Reasoning

• URL: http://arxiv.org/abs/2502.12094v1
• Date: Mon, 17 Feb 2025 18:12:36 GMT
• Title: A Study on Leveraging Search and Self-Feedback for Agent Reasoning
• Authors: Karthikeyan K, Michelle Yuan, Elman Mansimov, Katerina Margatina, Anurag Pratik, Daniele Bonadiman, Monica Sunkara, Yi Zhang, Yassine Benajiba,
• Abstract summary: We investigate how search and model's self-feedback can be leveraged for reasoning tasks. First, we explore differences in ground-truth feedback and self-feedback during search for math reasoning.
• Score: 16.256600534996686
• License:
• Abstract: Recent works have demonstrated that incorporating search during inference can significantly improve reasoning capabilities of language agents. Some approaches may make use of the ground truth or rely on model's own generated feedback. The search algorithm uses this feedback to then produce values that will update its criterion for exploring and exploiting various reasoning paths. In this study, we investigate how search and model's self-feedback can be leveraged for reasoning tasks. First, we explore differences in ground-truth feedback and self-feedback during search for math reasoning. Second, we observe limitations in applying search techniques to more complex tasks like tool-calling and design domain-specific approaches to address these gaps. Our experiments reveal challenges related to generalization when solely relying on self-feedback during search. For search to work effectively, either access to the ground-truth is needed or feedback mechanisms need to be carefully designed for the specific task.

Related papers

• Objective Metrics for Human-Subjects Evaluation in Explainable Reinforcement Learning [0.47355466227925036]
  Explanation is a fundamentally human process. Understanding the goal and audience of the explanation is vital. Existing work on explainable reinforcement learning (XRL) routinely does not consult humans in their evaluations. This paper calls on researchers to use objective human metrics for explanation evaluations based on observable and actionable behaviour.
  arXiv  Detail & Related papers  (2025-01-31T16:12:23Z)
• Enhancing LLM Reasoning with Reward-guided Tree Search [95.06503095273395]
  o1-like reasoning approach is challenging, and researchers have been making various attempts to advance this open area of research. We present a preliminary exploration into enhancing the reasoning abilities of LLMs through reward-guided tree search algorithms.
  arXiv  Detail & Related papers  (2024-11-18T16:15:17Z)
• Likelihood as a Performance Gauge for Retrieval-Augmented Generation [78.28197013467157]
  We show that likelihoods serve as an effective gauge for language model performance. We propose two methods that use question likelihood as a gauge for selecting and constructing prompts that lead to better performance.
  arXiv  Detail & Related papers  (2024-11-12T13:14:09Z)
• RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation [65.5353313491402]
  We introduce RethinkMCTS, which employs the Monte Carlo Tree Search (MCTS) algorithm to conduct thought-level searches before generating code. We construct verbal feedback from fine-turbo code execution feedback to refine erroneous thoughts during the search. We demonstrate that RethinkMCTS outperforms previous search-based and feedback-based code generation baselines.
  arXiv  Detail & Related papers  (2024-09-15T02:07:28Z)
• Tree Search for Language Model Agents [69.43007235771383]
  We propose an inference-time search algorithm for LM agents to perform exploration and multi-step planning in interactive web environments. Our approach is a form of best-first tree search that operates within the actual environment space. It is the first tree search algorithm for LM agents that shows effectiveness on realistic web tasks.
  arXiv  Detail & Related papers  (2024-07-01T17:07:55Z)
• RAR-b: Reasoning as Retrieval Benchmark [7.275757292756447]
  We transform reasoning tasks into retrieval tasks to evaluate reasoning abilities stored in retriever models. Recent decoder-based embedding models show great promise in narrowing the gap. We release Reasoning as Retrieval Benchmark (RAR-b), a holistic suite of tasks and settings to evaluate the reasoning abilities stored in retriever models.
  arXiv  Detail & Related papers  (2024-04-09T14:34:48Z)
• Beyond Semantics: Learning a Behavior Augmented Relevance Model with Self-supervised Learning [25.356999988217325]
  Relevance modeling aims to locate desirable items for corresponding queries. auxiliary query-item interactions extracted from user historical behavior data could provide hints to reveal users' search intents further. Our model builds multi-level co-attention for distilling coarse-grained and fine-grained semantic representations from both neighbor and target views.
  arXiv  Detail & Related papers  (2023-08-10T06:52:53Z)
• Zero-shot Clarifying Question Generation for Conversational Search [25.514678546942754]
  We propose a constrained clarifying question generation system which uses both question templates and query facets to guide the effective and precise question generation. Experiment results show that our method outperforms existing state-of-the-art zero-shot baselines by a large margin.
  arXiv  Detail & Related papers  (2023-01-30T04:43:02Z)
• Reannealing of Decaying Exploration Based On Heuristic Measure in Deep Q-Network [82.20059754270302]
  We propose an algorithm based on the idea of reannealing, that aims at encouraging exploration only when it is needed. We perform an illustrative case study showing that it has potential to both accelerate training and obtain a better policy.
  arXiv  Detail & Related papers  (2020-09-29T20:40:00Z)
• AutoOD: Automated Outlier Detection via Curiosity-guided Search and Self-imitation Learning [72.99415402575886]
  Outlier detection is an important data mining task with numerous practical applications. We propose AutoOD, an automated outlier detection framework, which aims to search for an optimal neural network model. Experimental results on various real-world benchmark datasets demonstrate that the deep model identified by AutoOD achieves the best performance.
  arXiv  Detail & Related papers  (2020-06-19T18:57:51Z)
• Contextual Search in the Presence of Adversarial Corruptions [33.28268414842846]
  We study contextual search, a generalization of binary search in higher dimensions. We show that these algorithms attain near-optimal regret in the absence of adversarial corruptions. Our techniques draw inspiration from learning theory, game theory, high-dimensional geometry, and convex analysis.
  arXiv  Detail & Related papers  (2020-02-26T17:25:53Z)

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.