Behavioural traces surface recurring LLM failure modes including overbidding, self-bidding, bankrupt TC initiation, and weak opponent-state adaptation that never appear in code agents.

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Two heuristic code agents outperform most tested LLMs, and behavioural traces surface recurring LLM failure modes including overbidding, self-bidding, bankrupt TC initiation, and weak opponent-state adaptation.quote0.917
  Abstract sentence summarising performance and failures.
• Overbid frequency, self-bidding rate, bankrupt-initiation patterns, and context-dependent offer calibration are failure modes invisible to both static evaluations and aggregate rankings like Eloclaim0.835
  key claim about the benchmark's unique diagnostic value
• Overbidding, self-bidding spirals, and undisciplined bluffing characterise failure.claim0.796
  Concrete failure signatures extracted from traces.
• Baseline LLM condition in IPD replicates prior findings: agents cooperate selectively only when opponent consistently cooperatesfinding0.782
  Replication of Fontana et al. 2025 findings in the paper's own Experiment 2 baseline condition
• Code agents operate on structured data with exact arithmetic, while LLMs must parse natural-language observations and track state across turns; some failures may partly reflect numerical parsing or working-memory limitationsclaim0.772
  discussion of potential confounds
• Do LLM failures in CATTLE TRADE reflect genuinely hard strategic problems or errors that novice humans also avoid?question0.772
  Open question about benchmarking against human players to calibrate difficulty.
• Sequences of contemporary Transformer-based LLM representations lack statistically significant indicators of observed 'consciousness' phenomena under the three stringent criteria.claim0.766
  Primary conclusion of the study based on temporal permutation analysis failing all three criteria.
• Conditional logic already suffices where LLMs still fail, as code agents avoid systematic failuresclaim0.766
  contrast between rule-based and LLM reasoning