Sepia

This week's paper is about conversational recommenders — systems that suggest things while you talk with them. The authors ask what changes when such a system remembers you across visits instead of starting fresh every time. Their answer involves several agents, a language model in the middle, and memory treated as part of the design rather than an afterthought.

The starting point is a familiar complaint. Most conversational recommenders treat each session on its own, which makes it hard to…

Agents that reach for tools through the Model Context Protocol now have a benchmark aimed at one specific worry: hallucination. Instead of asking only whether a task got done, the authors built tasks where a particular kind of confusion is the main risk, then watched what agents actually did. The goal is diagnosis, not just a score.

The authors start from a gap. Most benchmarks for agents that use the Model Context Protocol ask one question: did the task finish? When those benchmarks do look at…

Multi-turn negotiation is hard for AI agents. A new benchmark asks a plainer question than most: once the talking stops, does the agreement actually do anything? The authors find that saying yes and creating value are two different skills.

The benchmark is called TradeWar. It simulates several countries negotiating with one another. Instead of stopping when the parties reach an agreement, it takes the dialogue and turns it into concrete policies — tariffs and shares of trade — then runs those…

A new paper asks how groups of learning agents can reach cooperation when each one pays a local cost and the benefit is shared by all. The authors use climate-policy cooperation as their test case, but the real subject is agreement design: what happens when promises have teeth, and how much teeth is too much.

The researchers begin with an existing framework where several agents make decisions repeatedly and learn from the results. On top of that, they add a negotiation stage. Agents propose…