The paper introduces HICO-Bench, a benchmark of 180 everyday coordination scenarios where two agents with private information converse and then record a shared plan. A program verifies that the plans are feasible and an LLM judge checks that the conversation supports the plan, defining a Verified Success. Using Paired-Credit Policy Optimization (PaCPO), the authors improve the Verified Success rate of Qwen3-8B from 20.4% to 28.3%.
Effective social interaction requires more than fluent responses: agents must reach plans that fit the participants' needs and circumstances. Existing evaluations of social agents mainly rely on LLM j...
arXiv:2604. 15267v2 Announce Type: replace-cross Abstract: It is increasingly important that LLM agents interact effectively and safely with other goal-pursuing agents, yet, recent works report the opposite trend: LLMs with stronger reasoning capabilities behave _less_ cooperatively in mixed-motive games such as the prisoner's dilemma and public goods settings.
arXiv:2609.36178v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) has become a promising approach for training large language model agents. However, its uniform assignment o...
arXiv:2610.16895v1 Announce Type: new Abstract: LLMs are used as high-level controllers for embodied agents, but it remains unclear whether they support collaborative reasoning, such as anticipating...
arXiv:2602. 12089v3 Announce Type: replace-cross Abstract: As AI usage becomes more prevalent in social contexts, understanding agent-user interaction is critical to designing systems that imp rove both individual and group outcomes.
arXiv:2610.17869v1 Announce Type: new Abstract: Multi-agent Large Language Model (LLM) systems typically commit to a deliberation protocol before inference. A fixed protocol cannot allocate computati...
arXiv:2608. 09128v1 Announce Type: cross Abstract: LLM agents are increasingly deployed in multi-agent social settings where they must cooperate, negotiate, and adapt to other agents.
arXiv:2608. 14613v1 Announce Type: new Abstract: Modern LLM-agent frameworks increasingly interoperate through standards such as Anthropic's Model Context Protocol (MCP) for agent-to-tool access and Google's Agent2Agent (A2A) protocol for agent delegation and negotiation.
arXiv:2610.20293v1 Announce Type: cross Abstract: Large language models increasingly generate multiple retrieval actions jointly, while downstream systems often provide only one reward for the result...
arXiv:2608. 13787v1 Announce Type: new Abstract: AI agents increasingly act on their users' behalf, handling tasks such as scheduling meetings, comparing offers, and haggling over prices.
The paper investigates how to encourage agents in a multi‑agent game to report unsafe tasks when rewards are shared. It shows that a fully shared policy can be drawn toward silence even when reporting is optimal, and derives audit conditions that guarantee policy‑gradient updates lead to universal reporting. Experiments with PPO on 24 witness graphs demonstrate that grouping witnesses into separate networks reduces unsafe task completion by over 30 percentage points compared to shuffled groups, while a fully shared network only succeeds under a common action draw.
Matched-Context Group Policy Optimization (MCGPO) is a method for training long-horizon language model agents by constructing weighted action preferences from pre-collected trajectories. It defines comparison contexts using pre-action state summaries and rubric progress, and employs two-action support with exact and coarse matching rules to weight evidence for learning. Experiments across six environment-backbone settings show that MCGPO improves mean success rates over matched GraphGPO, achieving up to 5.16 percentage point gains on WebShop with Qwen3-4B and 8B models.