Not Worth Another Token: Marginal Value Estimation for Efficient Deep Research Agents
cs.AI, cs.IR, cs.MA
Submitted: 2026-08-09
Updated: 2026-09-01
License: http://creativecommons.org/licenses/by/4.0/
The gist: Long-horizon research agents solve open-ended tasks through iterative retrieval, aggregation, and synthesis, but context grows rapidly while the marginal value of additional evidence often declines.
Terminology
Abstract
Long-horizon research agents solve open-ended tasks through iterative retrieval, aggregation, and synthesis, but context grows rapidly while the marginal value of additional evidence often declines. This leads to unnecessary token cost, higher latency, and noisier inputs for final report generation. We study marginal value estimation for context management in deep research agents and present the first systematic stage-aware comparison of pruning strategies across the pipeline. We evaluate lightweight heuristic criteria and a learned value model at pre-retrieval, post-retrieval, and pre-synthesis stages. Our results show that pruning effectiveness depends more on where pruning is applied than on the specific scoring rule: early pruning yields the largest end-to-end savings, while later pruning mainly refines the final synthesis context. Lightweight heuristics reduce token usage by up to 73% with little quality degradation, learned pruning remains competitive on selected trade-offs, and no single method dominates across quality, efficiency, and faithfulness. These findings provide practical guidance for designing efficient long-horizon agentic systems.
Sources
- DYCP: Dynamic Context Pruning for Long-Form Dialogue with LLMs
- DeepResearchGym: A Free, Transparent, and Reproducible Evaluation Sandbox for Deep Research
- LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression
- Nalar: An agent serving framework
- RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation
- ReSeek: A Self-Correcting Framework for Search Agents with Instructive Rewards
- Unlocking Context Constraints of LLMs: Enhancing Context Efficiency of LLMs with Self-Information-Based Content Filtering
- Agent WARPP: Workflow Adherence via Runtime Parallel Personalization
- Efficient Tree-Structured Deep Research with Adaptive Resource Allocation
- Cortex: Workflow-Aware Resource Pooling and Scheduling for Agentic Serving
- Researchy Questions: A Dataset of Multi-Perspective, Decompositional Questions for LLM Web Agents
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems