Reinforced Agent: Inference-Time Feedback for Tool-Calling Agents

• URL: http://arxiv.org/abs/2604.27233v1
• Date: Wed, 29 Apr 2026 22:09:47 GMT
• Title: Reinforced Agent: Inference-Time Feedback for Tool-Calling Agents
• Abstract summary: We introduce Helpfulness-Harmfulness metrics to measure the tradeoff between agent feedback and reviewer feedback.<n>We evaluate our approach on BFCL and Tau2-Bench (multi-turn stateful scenarios), achieving +5.5% on irrelevance detection and +7.1% on multi-turn tasks.<n>Our metrics reveal that reviewer model choice is critical: the reasoning model o3-mini achieves a 3:1 benefit-to-risk ratio versus 2.1:1 for GPT-4o.
• Score: 6.158612515104146
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Tool-calling agents are evaluated on tool selection, parameter accuracy, and scope recognition, yet LLM trajectory assessments remain inherently post-hoc. Disconnected from the active execution loop, such assessments identify errors that are usually addressed through prompt-tuning or retraining, and fundamentally cannot course-correct the agent in real time. To close this gap, we move evaluation into the execution loop at inference time: a specialized reviewer agent evaluates provisional tool calls prior to execution, shifting the paradigm from post-hoc recovery to proactive evaluation and error mitigation. In practice, this architecture establishes a clear separation of concerns between the primary execution agent and a secondary review agent. As with any multi-agent system, the reviewer can introduce new errors while correcting others, yet no prior work to our knowledge has systematically measured this tradeoff. To quantify this tradeoff, we introduce Helpfulness-Harmfulness metrics: helpfulness measures the percentage of base agent errors that feedback corrects; harmfulness measures the percentage of correct responses that feedback degrades. These metrics directly inform reviewer design by revealing whether a given model or prompt provides net positive value. We evaluate our approach on BFCL (single-turn) and Tau2-Bench (multi-turn stateful scenarios), achieving +5.5% on irrelevance detection and +7.1% on multi-turn tasks. Our metrics reveal that reviewer model choice is critical: the reasoning model o3-mini achieves a 3:1 benefit-to-risk ratio versus 2.1:1 for GPT-4o. Automated prompt optimization via GEPA provides an additional +1.5-2.8%. Together, these results demonstrate a core advantage of separating execution and review: the reviewer can be systematically improved through model selection and prompt optimization, without retraining the base agent.

Related papers

• CAFE: Self-Improving Search Agents Need Co-Evolving Feedback [64.5257526832476]
  Outcome-supervised search agents learn when and how to retrieve evidence, but terminal rewards neither localize intermediate errors nor redirect an ongoing trajectory before those errors compound.<n>Treating corrective feedback as a learned in-trajectory intervention couples the two roles: the agent must decide when to request and use feedback, while the critic must infer useful corrections from outcome-confounded rollouts whose failure patterns shift as the agent improves.
  arXiv  Detail & Related papers  (2026-08-25T16:39:00Z)
• Closing the Reflection Gap: A Free Calibration Bonus for Agentic RL [12.234169944475537]
  RefGRPO is a simple yet effective fix that augments standard RL algorithms with two key ingredients.<n>A free calibration bonus computed by contrasting the agent's own reflection with the actual outcome.<n>The resulting reflection turns the agent into its own verifier grounded in environment feedback.
  arXiv  Detail & Related papers  (2026-06-12T07:47:15Z)
• ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling [57.42714978834704]
  ExComm is a communication protocol for exploration-stage agentic test-time scaling.<n>We show that ExComm consistently outperforms strong test-time scaling baselines.
  arXiv  Detail & Related papers  (2026-05-21T07:38:44Z)
• Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents? [61.49434544687523]
  We introduce REFLECT, a meta-evaluation benchmark targeting fine-grained failure detection in agentic environments.<n> REFLECT defines a detailed taxonomy of process- and outcome-level failure modes, instantiated by performing controlled and localized interventions.<n>Our experiments show that even the best-performing models achieve overall accuracies below 55% across reasoning, tool-use, and report-quality failures.
  arXiv  Detail & Related papers  (2026-05-18T23:55:08Z)
• Talk, Evaluate, Diagnose: User-aware Agent Evaluation with Automated Error Analysis [3.3237915628874632]
  We argue that effective agent evaluation goes beyond correctness alone, incorporating conversation quality, efficiency and systematic diagnosis of agent errors.<n>We propose new metrics that capture both turn efficiency and intermediate progress of the agent.<n>We show that our TED framework reveals new insights regarding agent performance across models and user expertise levels.
  arXiv  Detail & Related papers  (2026-03-16T16:14:28Z)
• Evaluate-as-Action: Self-Evaluated Process Rewards for Retrieval-Augmented Agents [24.080021799509847]
  textscEvalAct (Evaluate-as-Action) converts implicit retrieval quality assessment into an explicit action.<n>textscEvalAct achieves the best average accuracy, with the largest gains on multi-hop tasks.
  arXiv  Detail & Related papers  (2026-03-10T05:22:40Z)
• Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification [71.98473277917962]
  Recent advances in Deep Research Agents (DRAs) are transforming automated knowledge discovery and problem-solving.<n>We propose an alternative paradigm: self-evolving the agent's ability by iteratively verifying the policy model's outputs, guided by meticulously crafted rubrics.<n>We present DeepVerifier, a rubrics-based outcome reward verifier that leverages the asymmetry of verification.
  arXiv  Detail & Related papers  (2026-01-22T09:47:31Z)
• How can we assess human-agent interactions? Case studies in software agent design [52.953425368394306]
  We make two major steps towards the rigorous assessment of human-agent interactions.<n>We propose PULSE, a framework for more efficient human-centric evaluation of agent designs.<n>We deploy the framework on a large-scale web platform built around the open-source software agent OpenHands.
  arXiv  Detail & Related papers  (2025-10-10T19:04:28Z)
• Pairwise or Pointwise? Evaluating Feedback Protocols for Bias in LLM-Based Evaluation [57.380464382910375]
  We show that the choice of feedback protocol for evaluation can significantly affect evaluation reliability and induce systematic biases.<n>We find that generator models can flip preferences by embedding distractor features.<n>We offer recommendations for choosing feedback protocols based on dataset characteristics and evaluation objectives.
  arXiv  Detail & Related papers  (2025-04-20T19:05:59Z)
• On the Role of Feedback in Test-Time Scaling of Agentic AI Workflows [71.92083784393418]
  Agentic AI (systems that autonomously plan and act) are becoming widespread, yet their task success rate on complex tasks remains low.<n>Inference-time alignment relies on three components: sampling, evaluation, and feedback.<n>We introduce Iterative Agent Decoding (IAD), a procedure that repeatedly inserts feedback extracted from different forms of critiques.
  arXiv  Detail & Related papers  (2025-04-02T17:40:47Z)

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.