paper-with-me

Papers

Agora: Enhancing LLM Agent Reasoning Via Auction-Based Task Allocation

2026-07-10 · Kaiji Zhou, Ales Leonardis, Yue Feng arxiv

Enhancing the reasoning capabilities of large language model (LLM) agents requires effective orchestration of diverse expert models and tools. However, existing frameworks typically call APIs based on coarse-grained matching between tasks and the functions of expert models or tools, while overlooking critical factors such as performance variability and cost efficiency among functionally similar alternatives. To address this, we propose Agora, a framework that introduces an incentive-compatible auction mechanism for dynamically allocating tasks to expert models and tools. By treating reasoning steps as tradeable items, Agora enables agents to bid based on their rectified competence-ensuring that critical logic is routed to the most capable solver rather than the most overconfident one. Evaluations across five benchmarks show that Agora improves over matched single-model, routing, and cascade baselines under comparable candidate pools, while exposing a controllable cost-quality trade-off through a single auction parameter.

📄 PDF Abstract BibTeX arXiv:2607.09600

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning

2026-06-23 · Honglin Guo, Qi Zhang, Yu Zhang, Weijie Li 외 arxiv

Large language models are increasingly deployed as agents that reason over documents rather than answer from parametric knowledge. We study archive-grounded reasoning: locating sparse evidence across a large, messy colle…

Agora: Toward Autonomous Bug Detection in Production-Level Consensus Protocols with LLM Agents

2026-05-28 · Xiang Liu, Sa Song, Zhaowei Zhang, Huiying Lan 외 arxiv

Consensus protocols form the backbone of distributed systems and blockchains, where implementation bugs can cause data corruption and financial losses. While LLM-based approaches show promise in code analysis, they strug…

Unifying Language Agent Algorithms with Graph-based Orchestration Engine for Reproducible Agent Research

2025-05-30 · Qianqian Zhang, Jiajia Liao, Heting Ying, Yibo Ma 외

Language agents powered by large language models (LLMs) have demonstrated remarkable capabilities in understanding, reasoning, and executing complex tasks. However, developing robust agents presents significant challenge…

Mathematical Reasoning

InfoBid: A Simulation Framework for Studying Information Disclosure in Auctions with Large Language Model-based Agents

2025-03-26 · Yue Yin

In online advertising systems, publishers often face a trade-off in information disclosure strategies: while disclosing more information can enhance efficiency by enabling optimal allocation of ad impressions, it may los…

Language ModelingLanguage ModellingLarge Language Model

AI Trading's Alpha Singularity: Emergent Market Reasoning through Agent-to-Agent Self-Evolution

2026-06-28 · Yuqi Li, Siyuan Liu, Bingjun Liu arxiv

Automated alpha mining holds the scoring function fixed and varies the search algorithm over it. A search that converges against a fixed scorer overfits whatever the scorer cannot penalize, a primary cause of the out-of-…