Pith. sign in

REVIEW 5 cited by

Efficacy of Language Model Self-Play in Non-Zero-Sum Games

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.18872 v2 pith:G6C253PI submitted 2024-06-27 cs.CL

Efficacy of Language Model Self-Play in Non-Zero-Sum Games

classification cs.CL
keywords self-playlanguagemodelscooperativedondcompetitivedealfully
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Game-playing agents like AlphaGo have achieved superhuman performance through self-play, which is theoretically guaranteed to yield optimal policies in competitive games. However, most language tasks are partially or fully cooperative, so it is an open question whether techniques like self-play can effectively be used to improve language models. We empirically investigate this question in a negotiation game setting known as Deal or No Deal (DoND). Crucially, the objective in DoND can be modified to produce a fully cooperative game, a strictly competitive one, or anything in between. We finetune language models in self-play over multiple rounds of filtered behavior cloning in DoND for each of these objectives and evaluate them in self-play and in collaboration with humans. We find that language models improve substantially in self-play, achieving 14-17x higher scores in task reward after finetuning. Further, the trained models generalize to both cooperation and competition with humans, scoring 2.5-6x higher than base models. We view these results as an early promising sign for language model self-play in cooperative settings, despite a lack of theoretical guarantees.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. The Attacker in the Mirror: Breaking Self-Consistency in Safety via Anchored Bipolicy Self-Play

    cs.AI 2026-05 unverdicted novelty 7.0

    Anchored Bipolicy Self-Play trains role-specific LoRA adapters on a frozen base model to break self-consistency collapse in self-play red-teaming, yielding up to 100x parameter efficiency and stronger safety on Qwen2....

  2. Using Cognitive Models to Improve Language Model Simulation of Human Persuasion Games

    cs.AI 2026-06 unverdicted novelty 6.0

    Equation-to-Behavior Prompting lets large LLMs match cognitive models like Bayesian updating in persuasion games; RL training cuts small-model belief error by 26.5% and improves diverse training outcomes by 2.5-12%.

  3. Talk is Cheap, Communication is Hard: Dynamic Grounding Failures and Repair in Multi-Agent Negotiation

    cs.MA 2026-05 unverdicted novelty 6.0

    LLM agent dyads fail to reach Pareto-optimal resource allocations in an iterated negotiation game due to dynamic grounding failures including anchoring, perfunctory fairness, and lost commitments, despite individual c...

  4. Talk is Cheap, Communication is Hard: Dynamic Grounding Failures and Repair in Multi-Agent Negotiation

    cs.MA 2026-05 unverdicted novelty 6.0

    LLM agent pairs in a resource allocation negotiation game fail to reach Pareto-optimal outcomes due to dynamic grounding failures such as loss of interaction history, anchoring, and referential errors.

  5. Interactive Critique-Revision Training for Reliable Structured LLM Generation

    cs.LG 2026-05 unverdicted novelty 5.0

    DPA-GRPO trains a generator-verifier pair via group-relative policy optimization on paired counterfactual actions, improving structured output accuracy on TaxCalcBench over zero-shot and generator-only baselines.