Ares: Adaptive Reasoning Effort Selection for Efficient LLM Agents

• URL: http://arxiv.org/abs/2603.07915v1
• Date: Mon, 09 Mar 2026 03:17:29 GMT
• Title: Ares: Adaptive Reasoning Effort Selection for Efficient LLM Agents
• Abstract summary: Ares is a framework for per-step dynamic reasoning effort selection tailored for multi-step agent tasks.<n>We develop a data generation pipeline that identifies the minimum reasoning effort required for successful step completion.<n>We evaluate Ares on a diverse set of agent tasks, including TAU-Bench for tool use agents, BrowseComp-Plus for deep-research agents, and WebArena for web agents.
• Score: 30.48395228595732
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern agents powered by thinking LLMs achieve high accuracy through long chain-of-thought reasoning but incur substantial inference costs. While many LLMs now support configurable reasoning levels (e.g., high/medium/low), static strategies are often ineffective: using low-effort modes at every step leads to significant performance degradation, while random selection fails to preserve accuracy or provide meaningful cost reduction. However, agents should reserve high reasoning effort for difficult steps like navigating complex website structures, while using lower-effort modes for simpler steps like opening a target URL. In this paper, we propose Ares, a framework for per-step dynamic reasoning effort selection tailored for multi-step agent tasks. Ares employs a lightweight router to predict the lowest appropriate reasoning level for each step based on the interaction history. To train this router, we develop a data generation pipeline that identifies the minimum reasoning effort required for successful step completion. We then fine-tune the router to predict these levels, enabling plug-and-play integration for any LLM agents. We evaluate Ares on a diverse set of agent tasks, including TAU-Bench for tool use agents, BrowseComp-Plus for deep-research agents, and WebArena for web agents. Experimental results show that Ares reduces reasoning token usage by up to 52.7% compared to fixed high-effort reasoning, while introducing minimal degradation in task success rates.

Related papers

• ProgRouter: Online Progress-Guided Orchestration for Multi-Agent LLM Workflows under Quality-Cost Tradeoffs [20.369237729934664]
  Multi-agent large language model (LLM) have emerged as a powerful paradigm for solving complex, open-ended tasks.<n>Existing cascade routing methods make one-shot, state-dependent decisions and cannot adapt to the dynamic, state-dependent nature of multi-step query-level decisions.<n>We present Prog, an online progress-guided routing framework that adaptively selects LLM agents across workflow steps to preserve task-solving quality while adhering to time and cost budgets.
  arXiv  Detail & Related papers  (2026-08-26T16:42:02Z)
• DLLM Agent: See Farther, Run Faster [94.74432470237817]
  Diffusion large language models (DLLMs) have emerged as an alternative to autoregressive (AR) decoding with appealing efficiency and modeling properties.<n>We study this in a controlled setting by instantiatingDLLM and AR backbones within the same agent workflow.<n>We find thatDLLM Agents are on average over 30% faster end to end than AR agents, with some cases exceeding 8x speedup.
  arXiv  Detail & Related papers  (2026-02-07T09:01:18Z)
• Optimizing Agentic Workflows using Meta-tools [3.3298825663516403]
  Agentic AI enables LLM to dynamically reason, plan, and interact with tools to solve complex tasks.<n>This work introduces Agent Optimization (AWO), a framework that identifies and optimize redundant tool execution patterns.<n>AWO reduces the number of LLM calls up to 11.9% while also increasing the task success rate by up to 4.2 percent points.
  arXiv  Detail & Related papers  (2026-01-29T17:43:08Z)
• RISER: Orchestrating Latent Reasoning Skills for Adaptive Activation Steering [62.63376387138257]
  We propose a plug-and-play intervention framework that adaptively steers large language models (LLMs) reasoning in activation space.<n>RISER constructs a library of reusable reasoning vectors and employs a lightweight Router to dynamically compose them for each input.<n>The Router is optimized via reinforcement learning under task-level rewards, activating latent cognitive primitives in an emergent and compositional manner.
  arXiv  Detail & Related papers  (2026-01-14T08:04:33Z)
• AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress [71.02263260394261]
  Large language models (LLMs) still encounter challenges in multi-turn decision-making tasks.<n>We build process reward models (PRMs) to evaluate each decision and guide the agent's decision-making process.<n>AgentPRM captures both the interdependence between sequential decisions and their contribution to the final goal.
  arXiv  Detail & Related papers  (2025-11-11T14:57:54Z)
• Route-and-Reason: Scaling Large Language Model Reasoning with Reinforced Model Router [9.580226379350737]
  Multi-step reasoning has proven essential for enhancing the problem-solving capabilities of Large Language Models.<n>Yet, many reasoning steps are relatively simple and can be handled by more efficient smaller-scale language models.<n>We propose R2-Reasoner, a novel framework that enables collaborative reasoning across heterogeneous LLMs.
  arXiv  Detail & Related papers  (2025-06-06T09:18:56Z)
• LLM-DSE: Searching Accelerator Parameters with LLM Agents [34.75581582648836]
  LLM-DSE is a multi-agent framework designed specifically for optimizing HLS directives.<n>Our explorer coordinates four agents: Router, Specialists, Arbitrator, and Critic.<n>LLM-DSE achieves substantial $2.55times$ performance gains over state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-05-18T01:31:42Z)
• ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning [53.817538122688944]
  We introduce Reinforced Meta-thinking Agents (ReMA) to elicit meta-thinking behaviors from Reasoning of Large Language Models (LLMs)<n>ReMA decouples the reasoning process into two hierarchical agents: a high-level meta-thinking agent responsible for generating strategic oversight and plans, and a low-level reasoning agent for detailed executions.<n> Empirical results from single-turn experiments demonstrate that ReMA outperforms single-agent RL baselines on complex reasoning tasks.
  arXiv  Detail & Related papers  (2025-03-12T16:05:31Z)
• Scaling Autonomous Agents via Automatic Reward Modeling And Planning [52.39395405893965]
  Large language models (LLMs) have demonstrated remarkable capabilities across a range of tasks.<n>However, they still struggle with problems requiring multi-step decision-making and environmental feedback.<n>We propose a framework that can automatically learn a reward model from the environment without human annotations.
  arXiv  Detail & Related papers  (2025-02-17T18:49:25Z)
• Division-of-Thoughts: Harnessing Hybrid Language Model Synergy for Efficient On-Device Agents [5.566936703366701]
  Division-of-Thoughts (DoT) is a collaborative reasoning framework leveraging the synergy between local and cloud-based language models.<n>DoT reduces the average reasoning time and API costs by 66.12% and 83.57%, while achieving comparable reasoning accuracy with the best baseline methods.
  arXiv  Detail & Related papers  (2025-02-06T02:40:25Z)
• AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents [52.13695464678006]
  This study enhances an LLM-based web agent by simply refining its observation and action space.<n>AgentOccam surpasses the previous state-of-the-art and concurrent work by 9.8 (+29.4%) and 5.9 (+15.8%) absolute points respectively.
  arXiv  Detail & Related papers  (2024-10-17T17:50:38Z)

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.