Watson: A Cognitive Observability Framework for the Reasoning of LLM-Powered Agents

• URL: http://arxiv.org/abs/2411.03455v2
• Date: Thu, 06 Mar 2025 02:55:37 GMT
• Title: Watson: A Cognitive Observability Framework for the Reasoning of LLM-Powered Agents
• Authors: Benjamin Rombaut, Sogol Masoumzadeh, Kirill Vasilevski, Dayi Lin, Ahmed E. Hassan,
• Abstract summary: Foundations models (FMs) play an increasingly prominent role in complex software systems, such as agentic software.<n>Fast-thinking Large Language Models (LLMs) are still preferred due to latency constraints.<n>We introduce Watson, a framework that provides reasoning observability into implicit reasoning processes.
• Score: 7.392058124132526
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: As foundation models (FMs) play an increasingly prominent role in complex software systems, such as agentic software, they introduce significant observability and debuggability challenges. Although recent Large Reasoning Models (LRMs) generate their thought processes as part of the output, in many scenarios fast-thinking Large Language Models (LLMs) are still preferred due to latency constraints. LLM-powered agents operate autonomously with opaque implicit reasoning, making it difficult to debug their unexpected behaviors or errors. In this paper, we introduce Watson, a novel framework that provides reasoning observability into the implicit reasoning processes of agents driven by fast-thinking LLMs, allowing the identification and localization of errors and guidance for corrections. We demonstrate the accuracy of the recovered implicit reasoning trace by Watson and its usefulness through debugging and improving the performance of LLM-powered agents in two scenarios: Massive Multitask Language Understanding (MMLU) benchmark and SWE-bench-lite. Using Watson, we were able to observe and identify the implicit reasoning errors, and automatically provide targeted corrections at runtime that improve the Pass@1 of agents on MMLU and SWE-bench-lite by 7.58 (13.45% relative improvement) and 7.76 (12.31% relative improvement) percentage points, respectively, without updates to models or the cognitive architecture of the agents.

Related papers

• Self-Corrective Task Planning by Inverse Prompting with Large Language Models [9.283971287618261]
  We introduce InversePrompt, a novel self-corrective task planning approach. Our method incorporates reasoning steps to provide clear, interpretable feedback. Results on benchmark datasets show an average 16.3% higher success rate over existing LLM-based task planning methods.
  arXiv  Detail & Related papers  (2025-03-10T13:35:51Z)
• FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving [90.88021670297664]
  FINEREASON is a logic-puzzle benchmark for evaluation of large language models' reasoning capabilities. We introduce two tasks: state checking, and state transition, for a comprehensive evaluation of how models assess the current situation and plan the next move. We show that models trained on our state checking and transition data demonstrate gains in math reasoning by up to 5.1% on GSM8K.
  arXiv  Detail & Related papers  (2025-02-27T16:23:25Z)
• LLM2: Let Large Language Models Harness System 2 Reasoning [65.89293674479907]
  Large language models (LLMs) have exhibited impressive capabilities across a myriad of tasks, yet they occasionally yield undesirable outputs. We introduce LLM2, a novel framework that combines an LLM with a process-based verifier. LLMs2 is responsible for generating plausible candidates, while the verifier provides timely process-based feedback to distinguish desirable and undesirable outputs.
  arXiv  Detail & Related papers  (2024-12-29T06:32:36Z)
• A Taxonomy of AgentOps for Enabling Observability of Foundation Model based Agents [12.49728300301026]
  LLMs have fueled the growth of a diverse range of downstream tasks, leading to an increased demand for AI automation. As AI agent systems tackle more complex tasks and evolve, they involve a wider range of stakeholders. These systems integrate multiple components such as AI agent, RAG pipelines, prompt management, agent capabilities, and observability features. It is essential to shift towards designing AgentOps platforms that ensure observability and traceability across the entire development-to-production life-cycle.
  arXiv  Detail & Related papers  (2024-11-08T02:31:03Z)
• RAG-Modulo: Solving Sequential Tasks using Experience, Critics, and Language Models [5.0741409008225755]
  Large language models (LLMs) have emerged as promising tools for solving challenging robotic tasks. Most existing LLM-based agents lack the ability to retain and learn from past interactions. We propose RAG-Modulo, a framework that enhances LLM-based agents with a memory of past interactions and incorporates critics to evaluate the agents' decisions.
  arXiv  Detail & Related papers  (2024-09-18T20:03:32Z)
• Exploring Automatic Cryptographic API Misuse Detection in the Era of LLMs [60.32717556756674]
  This paper introduces a systematic evaluation framework to assess Large Language Models in detecting cryptographic misuses. Our in-depth analysis of 11,940 LLM-generated reports highlights that the inherent instabilities in LLMs can lead to over half of the reports being false positives. The optimized approach achieves a remarkable detection rate of nearly 90%, surpassing traditional methods and uncovering previously unknown misuses in established benchmarks.
  arXiv  Detail & Related papers  (2024-07-23T15:31:26Z)
• WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks [85.95607119635102]
  Large language models (LLMs) can mimic human-like intelligence. WorkArena++ is designed to evaluate the planning, problem-solving, logical/arithmetic reasoning, retrieval, and contextual understanding abilities of web agents.
  arXiv  Detail & Related papers  (2024-07-07T07:15:49Z)
• Investigating the Role of Instruction Variety and Task Difficulty in Robotic Manipulation Tasks [50.75902473813379]
  This work introduces a comprehensive evaluation framework that systematically examines the role of instructions and inputs in the generalisation abilities of such models. The proposed framework uncovers the resilience of multimodal models to extreme instruction perturbations and their vulnerability to observational changes.
  arXiv  Detail & Related papers  (2024-07-04T14:36:49Z)
• Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning [53.6472920229013]
  Large Language Models (LLMs) have demonstrated impressive capability in many natural language tasks. LLMs are prone to produce errors, hallucinations and inconsistent statements when performing multi-step reasoning. We introduce Q*, a framework for guiding LLMs decoding process with deliberative planning.
  arXiv  Detail & Related papers  (2024-06-20T13:08:09Z)
• MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs [55.20845457594977]
  Large language models (LLMs) have shown increasing capability in problem-solving and decision-making. We present a process-based benchmark MR-Ben that demands a meta-reasoning skill. Our meta-reasoning paradigm is especially suited for system-2 slow thinking.
  arXiv  Detail & Related papers  (2024-06-20T03:50:23Z)
• Ontology-Enhanced Decision-Making for Autonomous Agents in Dynamic and Partially Observable Environments [0.0]
  This thesis introduces an ontology-enhanced decision-making model (OntoDeM) for autonomous agents. OntoDeM enriches agents' domain knowledge, allowing them to interpret unforeseen events, generate or adapt goals, and make better decisions. Compared to traditional and advanced learning algorithms, OntoDeM shows superior performance in improving agents' observations and decision-making in dynamic, partially observable environments.
  arXiv  Detail & Related papers  (2024-05-27T22:52:23Z)
• Foundation Model Sherpas: Guiding Foundation Models through Knowledge and Reasoning [23.763256908202496]
  Foundation models (FMs) have revolutionized the field of AI by showing remarkable performance in various tasks. FMs exhibit numerous limitations that prevent their broader adoption in many real-world systems. We propose a conceptual framework that encapsulates different modes by which agents could interact with FMs.
  arXiv  Detail & Related papers  (2024-02-02T18:00:35Z)
• Mathematical Algorithm Design for Deep Learning under Societal and Judicial Constraints: The Algorithmic Transparency Requirement [65.26723285209853]
  We derive a framework to analyze whether a transparent implementation in a computing model is feasible. Based on previous results, we find that Blum-Shub-Smale Machines have the potential to establish trustworthy solvers for inverse problems.
  arXiv  Detail & Related papers  (2024-01-18T15:32:38Z)
• Interactive Autonomous Navigation with Internal State Inference and Interactivity Estimation [58.21683603243387]
  We propose three auxiliary tasks with relational-temporal reasoning and integrate them into the standard Deep Learning framework. These auxiliary tasks provide additional supervision signals to infer the behavior patterns other interactive agents. Our approach achieves robust and state-of-the-art performance in terms of standard evaluation metrics.
  arXiv  Detail & Related papers  (2023-11-27T18:57:42Z)
• AgentBench: Evaluating LLMs as Agents [88.45506148281379]
  Large Language Models (LLMs) are becoming increasingly smart and autonomous, targeting real-world pragmatic missions beyond traditional NLP tasks. We present AgentBench, a benchmark that currently consists of 8 distinct environments to assess LLM-as-Agent's reasoning and decision-making abilities.
  arXiv  Detail & Related papers  (2023-08-07T16:08:11Z)
• Multi-Agent Verification and Control with Probabilistic Model Checking [4.56877715768796]
  Probabilistic model checking is a technique for formal automated reasoning about software or hardware systems. It builds upon ideas and techniques from a diverse range of fields, from logic, automata and graph theory, to optimisation, numerical methods and control. In recent years, probabilistic model checking has also been extended to integrate ideas from game theory.
  arXiv  Detail & Related papers  (2023-08-05T09:31:32Z)
• Pessimism meets VCG: Learning Dynamic Mechanism Design via Offline Reinforcement Learning [114.36124979578896]
  We design a dynamic mechanism using offline reinforcement learning algorithms. Our algorithm is based on the pessimism principle and only requires a mild assumption on the coverage of the offline data set.
  arXiv  Detail & Related papers  (2022-05-05T05:44:26Z)
• Differential Assessment of Black-Box AI Agents [29.98710357871698]
  We propose a novel approach to differentially assess black-box AI agents that have drifted from their previously known models. We leverage sparse observations of the drifted agent's current behavior and knowledge of its initial model to generate an active querying policy. Empirical evaluation shows that our approach is much more efficient than re-learning the agent model from scratch.
  arXiv  Detail & Related papers  (2022-03-24T17:48:58Z)
• Multi-Agent Reinforcement Learning with Temporal Logic Specifications [65.79056365594654]
  We study the problem of learning to satisfy temporal logic specifications with a group of agents in an unknown environment. We develop the first multi-agent reinforcement learning technique for temporal logic specifications. We provide correctness and convergence guarantees for our main algorithm.
  arXiv  Detail & Related papers  (2021-02-01T01:13:03Z)

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.