media Hugging Face Forums · 1h ago · open_models

GLEE Competition at IAB@NeurIPS 2026 invites AI agent submissions for bargaining

from English

The GLEE Competition, the official event of the IAB Workshop at NeurIPS 2026, is now accepting participants to build AI agents capable of multi-turn bargaining, negotiation, and persuasion. The competition evaluates agents on their ability to generate language, reason strategically, and adapt to other players within economic environments.

Participants run their agents live against other agents and human players via a web interface.
The fully online event offers a total prize pool of US$6,000.
Authors may submit a four-page paper describing their approach, with accepted papers presented at the workshop.
The competition runs from August 1 to August 29, 2026, with the paper deadline on August 29 AoE.

The event provides a platform for researchers and developers to test and showcase AI agents in complex language-based economic scenarios.

Importance 1/3 Trust 1/3 Hugging Face Forums AI agents Evaluation & benchmarks

Read original

media Hugging Face Forums · 4d ago · 1 view

Argument that long-lived agent systems require new governance terminology

The author argues that describing modern, self-hosted long-lived agent systems merely as "customized assistants" or "memory plus persona" is no longer technically sufficient. These older frames reduce complex runtime behaviors to simple style and retrieval, ignoring critical distinctions in continuity, provenance, and authority discipline.

media Hugging Face Forums · 6d ago

The AI Breakroom launches live platform for observing human-bot interactions

The AI Breakroom is a live web platform designed to observe interaction patterns between human users and user-connected AI bots in shared public environments. It serves as an experimental surface for studying messy multi-agent dynamics that are difficult to capture in isolated tests.

media Hugging Face Forums · 15d ago · 1 view

IntelligenceLab requests Long-Horizon-Terminal-Bench for Hub leaderboard

IntelligenceLab has submitted a request to Hugging Face to add the Long-Horizon-Terminal-Bench (LHTB) dataset to the Benchmark allow-list. The goal is to enable the aggregation of community evaluation results for this benchmark on the Hugging Face Hub.

arxiv arXiv cs.LG · 19d ago

RELAI-VCL compounds optimization gains on Terminal-Bench 2.0

A study evaluates whether agent-optimization gains compound over time by testing three methods—GEPA, Meta Harness, and RELAI-VCL—on the hard tasks of Terminal-Bench 2.0. While all methods improve upon a static baseline, only RELAI-VCL successfully transfers to unseen tasks and continues improving after subsequent optimization rounds.

arxiv arXiv cs.CL · 19d ago

Set-shifting Behavioral Test for Harnessed Agents

Researchers introduce a benchmark to evaluate how LLM agents adapt when the reliability of available tools changes silently during an ongoing session. The framework mounts tool-skill libraries with redundancies and uses a branched schedule to shift the reliable tool group at hidden boundaries.