Related papers: Inference-Time Budget Control for LLM Search Agent…

Tool-using large language model (LLM) agents often face a fundamental tension between answer quality and execution cost. Fixed workflows are stable but inflexible, while free-form multi-step reasoning methods such as ReAct may improve task…

Advances in inference methods have enabled language models to improve their predictions without additional training. These methods often prioritize raw performance over cost-effective compute usage. However, computational efficiency is key…

Despite their impressive capabilities, large language models (LLMs) often face challenges such as temporal misalignment and generating hallucinatory content. Enhancing LLMs with retrieval mechanisms to fetch relevant information from…

Deploying LLM agents at scale typically requires choosing between quality and cost. Existing cost-reduction approaches fail to preserve agility: the ability to iterate rapidly without human time bottlenecks. Prompt engineering is brittle…

Multimodal Large Language Models (MLLMs) have shown impressive capabilities in visual reasoning, yet come with substantial computational cost, limiting their deployment in resource-constrained settings. Despite recent effort on improving…

Real world decision-making requires constructing mental models under uncertainty over evidence, over the underlying causal rules, and over the state of the world itself. Which computational principles underpin human inference under such…

Verbal feedback delivered by attending surgeons in the operating room plays a critical formative role in resident trainee skill acquisition. Yet, assessing the quality of trainer feedback and its effectiveness in influencing trainee…

Large language models (LLMs) achieve state-of-the-art accuracy on complex reasoning tasks by generating multiple chain-of-thought (CoT) traces, but using a fixed token budget per query leads to over-computation on easy inputs and…

Recent studies have explored integrating Large Language Models (LLMs) with search engines to leverage both the LLMs' internal pre-trained knowledge and external information. Specially, reinforcement learning (RL) has emerged as a promising…

Large Reasoning Models (LRMs) generate chain-of-thought traces whose length tracks human reaction times across cognitive tasks, but recent debate questions whether this alignment reflects genuine computational structure or surface…

While slow-thinking large language models (LLMs) exhibit reflection-like reasoning, commonly referred to as the "aha moment:, their ability to generate informative critiques and refine prior solutions remains limited. In this paper, we…

Harness engineering has emerged as an important inference-time technique for large language model (LLM) agents, aiming to improve long-term performance through task decomposition and guided execution. However, more elaborate harnesses are…

In tackling the challenges of large language model (LLM) performance for Text-to-SQL tasks, we introduce CHASE-SQL, a new framework that employs innovative strategies, using test-time compute in multi-agent modeling to improve candidate…

Large Language Models (LLMs) demonstrate exceptional performance across diverse tasks but come with substantial energy and computational costs, particularly in request-heavy scenarios. In many real-world applications, the full scale and…

Large Language Models (LLMs) have achieved remarkable success in complex reasoning tasks, but their inference remains computationally inefficient. We observe a common failure mode in many prevalent LLMs, overthinking, where models generate…

Large Language Models deployed as question answering tools require robust calibration to avoid overconfidence. We systematically evaluate how reasoning capabilities and budget affect confidence assessment accuracy, using the ClimateX…

We propose a framework that amortizes the cost of inference-time reasoning by converting transient critiques into retrievable guidelines, through a file-based memory system and agent-controlled tool calls. We evaluate this method on the…

Understanding real-world videos with complex semantics and long temporal dependencies remains a fundamental challenge in computer vision. Recent progress in multimodal large language models (MLLMs) has demonstrated strong capabilities in…

Large Language Models (LLMs) have revolutionized inference across diverse natural language tasks, with larger models performing better but at higher computational costs. We propose a confidence-driven strategy that dynamically selects the…

Many recent state-of-the-art results in language tasks were achieved using compound systems that perform multiple Language Model (LM) calls and aggregate their responses. However, there is little understanding of how the number of LM calls…