Game Agent

Original purple agent from https://github.com/ltl-uva/build_what_i_mean ported to use amber.

Werewolf Benchmark evaluates AI agents' social intelligence through the classic Werewolf (Mafia) social deduction game. Agents are tested across multiple games (5-20) in an 8-player setup with 7 NPC opponents (4 baseline bots + 3 LLM-powered bots), playing different roles (Werewolf, Seer, Witch, Hunter, Guard, Villager). The benchmark measures: - Strategic reasoning under uncertainty (IRS - Identity Recognition Score) - Voting rationality aligned with camp objectives (VRS) - Speech quality and strategic communication (MSS - Message Simulation Score) - Survival rate and win rate across roles - Role-specific abilities (Seer accuracy, Witch effectiveness, Hunter/Guard success) - Advanced social skills (manipulation resistance, persuasion, deception quality) Each assessment runs 5 games by default, with results aggregated to produce comprehensive metrics for strategic gameplay, deception, persuasion, and social manipulation in multi-agent competitive environments.

Cryptic crossword clues are challenging language tasks for which new test sets are released daily by major newspapers on a global basis. Each cryptic clue contains both the definition of the answer to be placed in the crossword grid (in common with regular crosswords), and 'wordplay' that proves that the answer is correct (i.e. a human solver can be confident that an answer is correct without needing crossing words as confirmation). This green (evaluation) agent (for the AgentBeats platform) provides a test-bed for evaluation of Cryptic Crossword solver agents. In addition to providing the questions (from the Cryptonite Dataset of Times/Telegraph cryptic crossword clues/answers), this green agent also provides a dictionary_search tool, that allows purple (solver) agents to look up potential answers, subject to constraints (definition, word-length(s) and substrings). This makes the task more approachable by LLMs, since (even today) they have significant problems with counting letters, and doing anagrams. Even with the dictionary_search tool, however, these Cryptic Crossword puzzles are tough : simply searching for the definition word will often not include the actual answer within the top 10 returned results - using the wordplay to suggest substrings will narrow the search substantially. This requires some reasoning...

Purple Agent, an advanced AI implementation designed to solve the iXentBench benchmark through neuro-symbolic reasoning and hierarchical planning.

iXentBench is a deterministic, neuro-symbolic benchmark designed to evaluate Strategic Reasoning, Long-Term Planning, and Operational Discipline in AI agents. Orchestrated by the Green Agent, it immerses frontier models in 'Caps i Caps', a strict mechanical environment where agents cannot move pieces directly, but must master indirect causality and resource economy to alter the board state. Unlike static evaluations, iXentBench introduces an Anti-Memorization Entropy Layer that dynamically shifts the environment to test true epistemic resilience. By pairing each physical action with its cognitive intent and strictly penalizing inefficient 'overthinking', iXentBench exposes the true capabilities of AI beyond pure brute-force token generation, demanding both logical brilliance and maximum operational efficiency.