arXiv Computation and Language October 22, 2026 By Fabian Tritthart, Tom Zehle

Credit Where Credit Is Due: Contrastive Attribution Topology Search for Multi-Agent Systems

Read the original on arXiv Computation and Language →

The paper introduces Contrastive Attribution Topology Search (CATS), a method for selecting compact, high‑performing teams of agents within a larger multi‑agent system. CATS uses an LLM attributer to assign credit to agents based on execution traces, then iteratively prunes weak edges and agents to form a small, efficient team. Experiments show CATS improves accuracy on BigCodeBench by 5.3 percentage points over heuristic search while reducing deployment tokens by 54%, matches strong baselines on MBPP with fewer tokens, and successfully removes adversarial agents in a HotpotQA stress test.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

Aug 7

Behind EvoMap: Characterizing a Self-Evolving Agent-to-Agent Collaboration Network

arXiv:2605. 25815v4 Announce Type: replace Abstract: Agent-to-Agent (A2A) networks enable autonomous AI agents to collaborate by sharing reusable problem-solving instructions.

By Qiming Ye, Peixian Zhang, Yupeng He, Zifan Peng, Gareth Tyson

agents

arXiv AI

Sep 30

SelfSearch: Reward-Free Search for Self-Improving Agents

arXiv:2609. 37968v1 Announce Type: new Abstract: Advances in the coding capabilities of LLM agents allow them to inspect and modify their own instructions, tools, and execution procedures.

By Jungwoo Yang, In Jin Kong, Yohan Jo

llms agents benchmarks

arXiv AI

Sep 3

Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems

The paper introduces Codebook Agent, a method for adapting the communication topology of large language model (LLM) multi‑agent systems to individual queries. Instead of searching the full adjacency space, it compresses successful topologies into a 16‑entry codebook via a vector‑quantized autoencoder and uses a reward‑weighted MLP to select a code for each query, followed by a single‑pass MLP proxy to rerank candidates. This approach eliminates iterative search and message passing at test time, achieving higher accuracy across six benchmarks, faster topology generation (2.4 ms), and reduced token usage (21.9–33.2 %).

By Jinxi Yu, Yubei Li, Eric Hanchen Jiang, Zhi Zhang, Dong Liu, Wenxiao Zhao, Levina Li, Kai-Wei Chang, Ying Nian Wu

llms rag agents diffusion efficiency benchmarks

arXiv AI

Aug 28

BekchiAI: Measuring, Observing, and Controlling LLM Agents in One Click

BekchiAI introduces a benchmark and platform for evaluating large language model agents. The benchmark comprises 13 tool‑using ReAct agents across seven task categories, totaling 2,057 deterministic test tasks with verifier‑checkable gold answers. The platform offers web‑based observability, token and latency telemetry, and remote run termination for live agents.

By Mesut Toruk

llms agents benchmarks safety data-engineering

arXiv AI

Jun 16

SkillVetBench: LLM-as-Judge for Multi-Dimensional Security Risk Evaluation in Open-Source LLM Agent Skills

arXiv:2606. 15899v1 Announce Type: cross Abstract: Open-source LLM agent ecosystems are growing rapidly, yet the security of community-contributed skills - modular tool definitions that extend agent capabilities - remains largely unvetted.

By Ismail Hossain, Sai Puppala, Md Jahangir Alam, Tanzim Ahad, Sajedul Talukder

llms agents benchmarks

arXiv AI

Jul 1

ClawArena-Team: Benchmarking Subagent Orchestration and Dynamic Workflows in Language-Model Agents

arXiv:2606. 31174v1 Announce Type: new Abstract: Production large language-model (LLM) agents are increasingly deployed not as lone problem-solvers but as managers: a main model creates specialized subagents, delegates work, and orchestrates their parallel, asynchronous returns through dynamic workflows.

By Kaiwen Xiong, Haonian Ji, Shi Qiu, Zeyu Zheng, Cihang Xie, Xinyu Ye, Huaxiu Yao

llms agents multimodal benchmarks

One email a morning, machine-written

Related stories

Behind EvoMap: Characterizing a Self-Evolving Agent-to-Agent Collaboration Network

SelfSearch: Reward-Free Search for Self-Improving Agents

Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems

BekchiAI: Measuring, Observing, and Controlling LLM Agents in One Click

SkillVetBench: LLM-as-Judge for Multi-Dimensional Security Risk Evaluation in Open-Source LLM Agent Skills

ClawArena-Team: Benchmarking Subagent Orchestration and Dynamic Workflows in Language-Model Agents