Large language models (LLMs) increasingly rely on multi-turn tool-integrated planning for knowledge-intensive and complex reasoning tasks. Existing implementations typically rely on a single agent, but they suffer from limited context length and noisy tool responses. A natural solution is to adopt a multi-agent framework with planner- and worker-agents to manage context. However, no existing methods support effective reinforcement learning post-training of tool-integrated multi-agent frameworks. To address this gap, we propose Multi-Agent Tool-Integrated Policy Optimization (MATPO), which enables distinct roles (planner and worker) to be trained within a single LLM instance using role-specific prompts via reinforcement learning. MATPO is derived from a principled credit assignment mechanism across planner and worker rollouts. This design eliminates the need to deploy multiple LLMs, which would be memory-intensive, while preserving the benefits of specialization. Experiments on GAIA-text, WebWalkerQA, and FRAMES show that MATPO consistently outperforms single-agent baselines by an average of 18.38% relative improvement in performance and exhibits greater robustness to noisy tool outputs. Our findings highlight the effectiveness of unifying multiple agent roles within a single LLM and provide practical insights for stable and efficient multi-agent RL training.

One of the country's biggest law firms has become the first to publicly announce that it has "hired" a robot lawyer to assist with bankruptcy cases. The robot, called ROSS, has been marketed as "the world's first artificially intelligent attorney." ROSS has joined the ranks of law firm BakerHostetler, which employs about 50 human lawyers just in its bankruptcy practice. The AI machine, powered by IBM's Watson technology, will serve as a legal researcher for the firm. It will be responsible for sifting through thousands of legal documents to bolster the firm's cases.

Lily Robotics, which promised an autonomous flying camera, is shutting down operations. Lily Robotics, the hyped drone startup that shutdown last month amid a consumer-protection civil suit from the San Francisco District Attorney's office, filed for Chapter 11 bankruptcy protection on Monday. In documents submitted to a U.S. district court in Delaware, Lily Robotics outlined its intentions to auction off intellectual property and refund customers, which it said was its first priority. "[Lily] wants to ensure no customers are harmed in this process," wrote Curtis Solsvig, a managing director at Goldin Associates who is named as the company's chief restructuring officer. Lily amassed more than $38 million in pre-orders from 61,450 customers in more than 80 countries, according to the filing.

In April several news sources reported that the law firm of Baker Hostetler had hired a legal robot called ROSS. This artificial intelligence system, built on IBM's famous Watson system, automates legal tasks like research and the preparation of legal memorandums in the narrow domain of bankruptcy law. Since then, other big law firms have joined the rush. ROSS Intelligence markets its product as a kind of artificial intelligent assistant: ask it questions in plain language, and legal research is presented. It sounds a lot like Siri, except instead of asking for baseball scores one can ask for relevant case law.

One of the country's biggest law firms has become the first to publicly announce that it has "hired" a robot lawyer to assist with bankruptcy cases. The robot, called ROSS, has been marketed as "the world's first artificially intelligent attorney." ROSS has joined the ranks of law firm BakerHostetler, which employs about 50 human lawyers just in its bankruptcy practice. The AI machine, powered by IBM's Watson technology, will serve as a legal researcher for the firm. It will be responsible for sifting through thousands of legal documents to bolster the firm's cases.

One of the country's biggest law firms has become the first to publicly announce that it has "hired" a robot lawyer to assist with bankruptcy cases. The robot, called ROSS, has been marketed as "the world's first artificially intelligent attorney." ROSS has joined the ranks of law firm BakerHostetler, which employs about 50 human lawyers just in its bankruptcy practice. The AI machine, powered by IBM's Watson technology, will serve as a legal researcher for the firm. It will be responsible for sifting through thousands of legal documents to bolster the firm's cases.

In this paper, we consider a distinctly bottom-up which generates arguments by performing a heuristic approach.