Adaptive Latent Agentic Reasoning
Quick Answer
This paper shows that The Adaptive Latent Agentic Reasoning (ALAR) framework enhances LLM agents by using compact latent reasoning for routine decisions and explicit chain-of-thought for complex ones, achieving up to 43.6% fewer tokens in search tasks and 84.6% in tool use while maintaining or improving task accuracy.
Key Points
- ALAR reduces reasoning verbosity in agents, improving efficiency.
- Achieves up to 43.6% fewer tokens in agentic search tasks.
- Reduces token generation by 84.6% in scenarios.
- Maintains comparable or better task accuracy with adaptive reasoning.
- Optimizes reasoning effort based on task complexity.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 02871v1 Announce Type: new Abstract: Large reasoning models improve performance by generating extended chain-of-thought (CoT) reasoning, but this behavior becomes inefficient when applied to agents. Current LLM agents often generate verbose textual reasoning at every decision step and allocate reasoning effort nearly uniformly across turns, leading to substantial inefficiency in multi-turn agentic trajectories.
We propose Adaptive Latent Agentic Reasoning (ALAR), a dual-mode framework that uses compact latent reasoning for routine turns and selectively escalates to explicit chain-of-thought when deeper deliberation is needed. ALAR learns latent reasoning by using the agent's actions as supervision anchors and is further optimized to use latent reasoning when it is sufficient for task success and reserve explicit CoT for harder decisions.
Experiments on agentic search and benchmarks show that ALAR maintains comparable or better task accuracy while substantially reducing generated tokens by up to 43. 6% in search and 84. 6% in tool use. These results demonstrate that ALAR improves the accuracy-efficiency trade-off of LLM agents by reducing unnecessary textual reasoning while preserving explicit deliberation for harder decision steps.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →TriAgent: Divergence-Aware Committees for Cost-Efficient Financial Sentiment Analysis
TriAgent introduces a cost-efficient multi-agent system for financial sentiment analysis, combining VADER, FinBERT, and Qwen2.5. It achieves an F1 score of ~0.87 with significant savings of $9.3M/year at a 10M-user scale compared to GPT-4o-mini, while also detecting hallucinations with an AUC of 0.90.