Related papers: Learning Agent Routing From Early Experience

A long-term goal of language agents is to learn and improve through their own experience, ultimately outperforming humans in complex, real-world tasks. However, training agents from experience data with reinforcement learning remains…

Reasoning-oriented Large Language Models (LLMs) often rely on generating explicit tokens step by step, and their effectiveness typically hinges on large-scale supervised fine-tuning or reinforcement learning. While Chain-of-Thought (CoT)…

Large language model (LLM) routing assigns each query to the most suitable model from an ensemble. We introduce LLMRouterBench, a large-scale benchmark and unified framework for LLM routing. It comprises over 400K instances from 21 datasets…

While reasoning-augmented large language models (RLLMs) significantly enhance complex task performance through extended reasoning chains, they inevitably introduce substantial unnecessary token consumption, particularly for simpler problems…

While large language models (LLMs) have been thoroughly evaluated for deductive and inductive reasoning, their proficiency in holistic rule learning in interactive environments remains less explored. We introduce RULEARN, a novel benchmark…

Lifelong learning is essential for intelligent agents operating in dynamic environments. Current large language model (LLM)-based agents, however, remain stateless and unable to accumulate or transfer knowledge over time. Existing…

People commonly leverage structured content to accelerate knowledge acquisition and research problem solving. Among these, roadmaps guide researchers through hierarchical subtasks to solve complex research problems step by step. Despite…

Large language model (LLM) routers improve the efficiency of multi-model systems by directing each query to the most appropriate model while leveraging the diverse strengths of heterogeneous LLMs. Most existing approaches frame routing as a…

Large Language Model (LLM) Agents, often trained with Reinforcement Learning (RL), are constrained by a dependency on human-curated data, limiting scalability and tethering AI to human knowledge. Existing self-evolution frameworks offer an…

Multimodal large language models (MLLMs) have heterogeneous strengths across OCR, chart understanding, spatial reasoning, visual question answering, cost, and latency. Effective MLLM routing therefore requires more than estimating query…

Deploying large language models (LLMs) in edge-cloud environments requires an efficient routing strategy to balance cost and response quality. Traditional approaches prioritize either human-preference data or accuracy metrics from benchmark…

Large language model (LLM) agents often rely on long sequences of low-level textual actions, resulting in large effective decision horizons and high inference cost. While prior work has focused on improving inference efficiency through…

Large Language Models (LLMs) have shown remarkable performance on general Question Answering (QA), yet they often struggle in domain-specific scenarios where accurate and up-to-date information is required. Retrieval-Augmented Generation…

When an LLM-based agent improves on a task, is the gain from the model itself or from the reasoning paradigm wrapped around it? We study this question by comparing six inference-time paradigms, namely Direct, CoT, ReAct, Plan-Execute,…

LLM-powered agents face a persistent challenge: learning from their execution experiences to improve future performance. While agents can successfully complete many tasks, they often repeat inefficient patterns, fail to recover from similar…

Recent work explores latent reasoning to improve reasoning efficiency by replacing explicit reasoning trajectories with continuous representations in a latent space, yet its effectiveness varies across settings. Analysis of model confidence…

Multi-agent systems using large language models (LLMs) have demonstrated impressive capabilities across various domains. However, current agent communication suffers from verbose output that overload context and increase computational…

Autonomous agents powered by large language models (LLMs) promise to accelerate scientific discovery end-to-end, but rigorously evaluating their capacity for verifiable discovery remains a central challenge. Existing benchmarks face a…

Large Language Models (LLMs) and Reinforcement Learning (RL) are two powerful approaches for building autonomous agents. However, due to limited understanding of the game environment, agents often resort to inefficient exploration and…

Large language models (LLMs) have demonstrated exceptional performance across a wide range of natural language tasks. However, selecting the optimal LLM to respond to a user query often necessitates a delicate balance between performance…