Pith. sign in

REVIEW 6 cited by

SMART: Self-Aware Agent for Tool Overuse Mitigation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.11435 v2 pith:JRABVH6D submitted 2025-02-17 cs.AI cs.CLcs.LG

classification cs.AIcs.CLcs.LG
keywords tooloverusereasoningagentknowledgemodelsparametricsmartagent
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Current Large Language Model (LLM) agents demonstrate strong reasoning and tool use capabilities, but often lack self-awareness, failing to balance these approaches effectively. This imbalance leads to Tool Overuse, where models unnecessarily rely on external tools for tasks solvable with parametric knowledge, increasing computational overhead. Inspired by human metacognition, we introduce SMART (Strategic Model-Aware Reasoning with Tools), a paradigm that enhances an agent's self-awareness to optimize task handling and reduce tool overuse. To support this paradigm, we introduce SMART-ER, a dataset spanning three domains, where reasoning alternates between parametric knowledge and tool-dependent steps, with each step enriched by rationales explaining when tools are necessary. Through supervised training, we develop SMARTAgent, a family of models that dynamically balance parametric knowledge and tool use. Evaluations show that SMARTAgent reduces tool use by 24% while improving performance by over 37%, enabling 7B-scale models to match its 70B counterpart and GPT-4o. Additionally, SMARTAgent generalizes to out-of-distribution test data like GSM8K and MINTQA, maintaining accuracy with just one-fifth the tool calls. These highlight the potential of strategic tool use to enhance reasoning, mitigate overuse, and bridge the gap between model size and performance, advancing intelligent and resource-efficient agent designs.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use

    cs.AI 2026-05 unverdicted novelty 7.0 of 10

    Model-adaptive tool necessity shows 26-54% mismatch with actual tool calls across LLMs, driven by nearly orthogonal hidden-state signals for cognition versus action.

  2. Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use

    cs.AI 2026-05 unverdicted novelty 6.0 of 10

    LLMs show a knowing-doing gap in tool use: they often recognize when tools are needed via internal states but fail to translate that into actual tool calls, with mismatches of 26-54% on arithmetic and factual tasks.

  3. When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoning

    cs.CL 2026-04 unverdicted novelty 6.0 of 10

    ATTC reduces 'Tool Ignored' errors in tool-integrated reasoning by adaptively trusting tool results according to generated code confidence, yielding 4.1-7.5% gains across models and datasets.

  4. UserBench: An Interactive Gym Environment for User-Centric Agents

    cs.AI 2025-07 conditional novelty 6.0 of 10

    A new multi-turn agent benchmark shows that current LLMs elicit fewer than 30% of user preferences and reach full intent alignment only about 20% of the time.

  5. ToolRL: Reward is All Tool Learning Needs

    cs.LG 2025-04 conditional novelty 6.0 of 10

    A principled reward design for tool selection and application in RL-trained LLMs delivers 17% gains over base models and 15% over SFT across benchmarks.

  6. The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project

    cs.LG 2026-03 unverdicted novelty 5.0 of 10

    The Workload-Router-Pool architecture is a 3D framework for LLM inference optimization that synthesizes prior vLLM work into a 3x3 interaction matrix and proposes 21 research directions at the intersections.

Pith tools