AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents

• URL: http://arxiv.org/abs/2603.27490v1
• Date: Sun, 29 Mar 2026 02:59:27 GMT
• Title: AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents
• Abstract summary: Large language models (LLMs) evolve into autonomous agents for long-horizon information-seeking.<n>Existing context management methods typically commit to a single fixed strategy throughout the entire trajectory.<n>We introduce a probabilistic framework that characterizes long-horizon success through two complementary dimensions: search efficiency and terminal precision.
• Score: 115.18197165538943
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As large language models (LLMs) evolve into autonomous agents for long-horizon information-seeking, managing finite context capacity has become a critical bottleneck. Existing context management methods typically commit to a single fixed strategy throughout the entire trajectory. Such static designs may work well in some states, but they cannot adapt as the usefulness and reliability of the accumulated context evolve during long-horizon search. To formalize this challenge, we introduce a probabilistic framework that characterizes long-horizon success through two complementary dimensions: search efficiency and terminal precision. Building on this perspective, we propose AgentSwing, a state-aware adaptive parallel context management routing framework. At each trigger point, AgentSwing expands multiple context-managed branches in parallel and uses lookahead routing to select the most promising continuation. Experiments across diverse benchmarks and agent backbones show that AgentSwing consistently outperforms strong static context management methods, often matching or exceeding their performance with up to $3\times$ fewer interaction turns while also improving the ultimate performance ceiling of long-horizon web agents. Beyond the empirical gains, the proposed probabilistic framework provides a principled lens for analyzing and designing future context management strategies for long-horizon agents.

Related papers

• ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL [30.70875568757697]
  Long-horizon agentic tasks require large language models to iteratively retrieve, integrate, and maintain dispersed information across multi-turn interactions.<n>Recent proactive context management methods allow models to edit their own working context with specialized tools.<n>We introduce ContextPilot, a proactive context management framework for long-horizon agentic reasoning.
  arXiv  Detail & Related papers  (2026-08-28T16:01:08Z)
• ACM: Agentic Context Management for Long Horizon Tasks [27.337726990282928]
  Agentic Context Management (ACM) is a framework that equips agents with purpose-built context editing tools.<n>Inspired by the interaction between short-term and long-term human memory, the agent autonomously decides when to compress its context.
  arXiv  Detail & Related papers  (2026-07-26T19:19:24Z)
• CoMIC: Collaborative Memory and Insights Circulation for Long-Horizon LLM Agents in Cloud-Edge Systems [23.892901534769067]
  lightweight Large Language Model (LLM) agents on edge servers can reduce latency and move agent services closer to users.<n>Fine-tuning edge models after deployment is costly and difficult to scale across heterogeneous nodes.<n>We propose textscCoMIC, a parameter-update-free cloud-edge framework for Collaborative Memory and Circulation Insights.
  arXiv  Detail & Related papers  (2026-05-30T14:45:39Z)
• Learning Agent-Compatible Context Management for Long-Horizon Tasks [79.09330817637205]
  We introduce Adaptive Context Management (AdaCoM), which trains an external LLM to manage the context of a frozen agent.<n>AdaCoM substantially improves performance by preserving task constraints and progress while pruning stale content.<n>The learned strategies reveal a Fidelity-Reliability Trade-off: agents with higher vanilla ReAct performance benefit from higher-fidelity context preservation, whereas lower-performing agents require more aggressive compression to stay within a reliable reasoning regime.
  arXiv  Detail & Related papers  (2026-05-29T03:21:08Z)
• InfoSeeker: A Scalable Hierarchical Parallel Agent Framework for Web Information Seeking [39.22757710468795]
  We present framework, a hierarchical framework based on principle of near-decomposability, containing a strategic textitHost, multiple textitManagers and parallel textitWorkers.<n>By leveraging aggregation and reflection mechanisms at the Manager layer, our framework enforces strict context isolation to prevent saturation and error propagation.<n>Our evaluation on two complementary benchmarks demonstrates both efficiency ($ 3-5 times$ speed-up) and effectiveness, achieving a $8.4%$ success rate on WideSearch-en and $52.9%$ accuracy on BrowseComp-zh
  arXiv  Detail & Related papers  (2026-04-03T11:19:17Z)
• AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts [78.33143446024485]
  We introduce textbfAgentLongBench, which evaluates agents through simulated environment rollouts based on Lateral Thinking Puzzles.<n>This framework generates rigorous interaction trajectories across knowledge-intensive and knowledge-free scenarios.
  arXiv  Detail & Related papers  (2026-01-28T16:05:44Z)
• Self-Manager: Parallel Agent Loop for Long-form Deep Research [33.21617483821564]
  This paper introduces Self-Manager, a parallel agent loop that enables asynchronous and concurrent execution.<n>The main thread can create multiple subthreads, each with its own isolated context, and manage them iteratively through Thread Control Blocks.<n>We benchmark Self-Manager on DeepResearch Bench, where it consistently outperforms existing single-agent loop baselines.
  arXiv  Detail & Related papers  (2026-01-25T15:18:53Z)
• InfiAgent: An Infinite-Horizon Framework for General-Purpose Autonomous Agents [36.740230738304525]
  InfiAgent keeps the agent's reasoning context strictly bounded regardless of task duration.<n>InfiAgent with a 20B open-source model is competitive with larger proprietary systems.
  arXiv  Detail & Related papers  (2026-01-06T17:35:57Z)
• Context as a Tool: Context Management for Long-Horizon SWE-Agents [38.950807465620365]
  We propose CAT, a new context management paradigm that elevates context maintenance to a callable tool integrated into the decision-making process of agents.<n> CAT formalizes a structured context workspace consisting of stable task semantics, condensed long-term memory, and high-fidelity short-term interactions.<n>We show that SWE-Compressor reaches a 57.6% solved rate and significantly outperforms ReAct-based agents and static compression baselines.
  arXiv  Detail & Related papers  (2025-12-26T17:15:47Z)
• SCOPE: Prompt Evolution for Enhancing Agent Effectiveness [53.75986399936395]
  Large Language Model (LLM) agents are increasingly deployed in environments that generate massive, dynamic contexts.<n>While agents have access to this context, their static prompts lack the mechanisms to manage it effectively.<n>We introduce textbfSCOPE (Self-evolving Context Optimization via Prompt Evolution)<n>We propose a Dual-Stream mechanism that balances tactical specificity (resolving immediate errors) with strategic generality (evolving long-term principles)
  arXiv  Detail & Related papers  (2025-12-17T12:25:05Z)
• Scaling Long-Horizon LLM Agent via Context-Folding [46.685552398338295]
  We introduce Context-Folding, a framework that empowers agents to actively manage their working context.<n>An agent can procedurally branch into a sub-trajectory to handle a subtask and then fold it upon completion, collapsing the intermediate steps while retaining a concise summary of the outcome.
  arXiv  Detail & Related papers  (2025-10-13T22:00:58Z)
• AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question Answering [51.07491603393163]
  tAgent is a framework that formulates multi-agent QA as a knowledge-graph-guided routing problem supervised by empirical performance signals.<n>By leveraging soft supervision and weighted aggregation of agent outputs, Agent learns principled collaboration schemes that capture the complementary strengths of diverse agents.
  arXiv  Detail & Related papers  (2025-10-06T23:20:49Z)
• UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios [63.67884284105684]
  We introduce textbfUltraHorizon, a novel benchmark that measures the foundational capabilities essential for complex real-world challenges.<n>Agents are designed in long-horizon discovery tasks where they must iteratively uncover hidden rules.<n>Our experiments reveal that LLM-agents consistently underperform in these settings, whereas human participants achieve higher scores.
  arXiv  Detail & Related papers  (2025-09-26T02:04:00Z)

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.