1 Introduction
Negotiation is increasingly delegated to software. Agents compare offers, draft counteroffers and, in some settings, conclude agreements on a principal’s behalf. Whether they do so better than people is therefore a practical question as well as a scientific one, and the existing answers point in different directions. Learned dialogue agents have claimed more value than their human partners while reaching agreement less often (Lewis et al. 2017; He et al. 2018). A system combining a language model with strategic planning played a seven-player negotiation game at a strong human level (Meta Fundamental AI Research Diplomacy Team (FAIR) et al. 2022). Studies that place language models against one another report large differences between models and low rates of agreement (Davidson et al. 2024; Bianchi et al. 2024; Abdelnabi et al. 2024).
These findings need not conflict, because negotiation performance is not a scalar. A negotiator may create joint value yet claim little of it, claim much yet frequently reach impasse, or perform well against a cooperative counterpart and poorly against a hardline one. The comparison between machines and people can therefore reverse with the outcome that is measured, the structure of the task, the design of the agent, the counterpart, and the constraints placed on what the agent may say. We pose the question in contingent form: under which conditions, on which outcomes, and by how much do machines out-negotiate humans?
Our approach has four parts. Section 3 develops a reduced-form model in which performance decomposes into the discovery of joint gains, the demand for a share and the rate of concession. Every parameter maps to a quantity recoverable from logged offers. Section 2 organises prior work in a coded map that shows where comparative evidence is thin. Sections 5–7 test pre-specified implications on human corpora, on published logs of language-model negotiations, and in a simulation of classical agents. Section 8 sets out an experimental design that extends the tests to current models.
The results are mostly negative for the predicted contingencies in observational data, and we report them in full. They nonetheless identify the dimension on which the comparison turns. Language models of 2023 divided fixed surpluses efficiently but failed to find the trades that integrative tasks reward. Human negotiators in comparable crowd-sourced tasks found a substantial part of them. Among those models, differences in capability translated into little claimed value, and move order mattered more.
2 Related literature
Theories of bargaining distinguish the division of a fixed surplus (Nash 1950; Rubinstein 1982) from the creation of joint value through trades across issues (Walton and McKersie 1965; Raiffa 1982; Lax and Sebenius 1986). Behavioural research shows that people often miss such trades (Thompson and Hastie 1990), that first offers anchor outcomes (Galinsky and Mussweiler 2001), and that displayed emotion shifts concessions (Van Kleef et al. 2004). Subjective outcomes matter alongside economic ones (Curhan et al. 2006).
Research on artificial negotiators has passed through three generations. Rule-based agents use explicit concession tactics (Faratin et al. 1998); they have been benchmarked in competitions (Baarslag et al. 2013) and against people (Lin et al. 2008; Lin and Kraus 2010; Melo et al. 2011; Mell et al. 2018). Learned agents trained on negotiation dialogue (Lewis et al. 2017; He et al. 2018; Yarats and Lewis 2018; Chawla et al. 2021) and agents for strategic games (Kramár et al. 2022; Meta Fundamental AI Research Diplomacy Team (FAIR) et al. 2022) introduced natural language and planning. Language-model agents are now evaluated in bilateral and multilateral settings (Fu et al. 2023; Davidson et al. 2024; Bianchi et al. 2024; Abdelnabi et al. 2024; Kwon et al. 2024; Xia et al. 2024; Vaccaro et al. 2025), and as negotiation coaches (Shea et al. 2024).
We coded 29 works by generation of agent, counterpart, outcome studied and direction of any comparison with people (Appendix E). Figure 1 summarises the coding. Evidence on claimed value is the most common, particularly for rule-based and learned agents facing people. Most evidence on language-model agents comes from play among models. Among the coded works, none compares a language-model negotiator with people on agreement or on honesty, and one does so on created value (Kwon et al. 2024). The map is a structured scoping review rather than a systematic one.1
3 A model of negotiation performance
3.1 Outcomes
A negotiation instance is , with a finite set of complete agreements, utilities and disagreement payoffs . Let , , and , the expected joint value of an agreement drawn at random.
The integrative share measures how much joint value the task allows negotiators to create. It is zero when no trade can raise joint value. For an agreement we define:
efficiency ;
created value when , the realised fraction of the integrative surplus, which is negative for agreements worse than a random one;
the share of surplus and the inequality .
We also record agreement , honesty and robustness to pressure.
3.2 Model
Assumption 1 (Pooled discovery). A dyad either implements an efficient agreement () or a compromise with . Negotiator identifies the efficient reallocation with probability when the counterpart’s stated priorities are informative, which occurs with probability . Identification by either party suffices.
Under Assumption 1,
3.3 Propositions
Proofs are in Appendix A.
Proposition 1 (Creation). Let . (a) increases in each . (b) Differences in expected efficiency between dyads are proportional to . (c) Discovery abilities are substitutes. Replacing one of two negotiators with ability by an agent with raises by . Replacing the second raises it by , which is smaller by .
Proposition 2 (Toughness). and . The set of pairs that agree shrinks in each and expands in each and in .
Proposition 3 (Exploitability). Holding the counterpart’s offers fixed, , which is negative if and only if .
Proposition 4 (Price of honesty). If overstating one’s outside option by lowers the counterpart’s opening by , then and . A prohibition of falsehoods reduces share only against a credulous counterpart. It weakly raises created value, so its net effect is non-positive when and ambiguous when .
Proposition 5 (Capability differences redistribute). With equal openings , . Differences in claiming behaviour are transfers between the parties, whereas discovery enters equation (1) symmetrically and benefits both.
Proposition 6 (Homogeneity). Identical negotiators divide the surplus equally and either always or never agree. If concession rates are drawn independently from a non-degenerate distribution, .
Figure 3 illustrates Propositions 1–3. The propositions are conditional. To obtain testable hypotheses about language-model agents, each is combined with an explicit conjecture about how such agents differ from people. Two examples are that they discover trades more often (H1, H2) and that they are more susceptible to pressure (H5). This way, a failed prediction can be traced to the conjecture rather than to the algebra. The data available here address the propositions behind H2, H3 and H7 directly, and those behind H1 and H4 in simulation. The design in Section 8 addresses all eight hypotheses for current models.
4 Data and empirical strategy
4.1 Data
Table 1 lists the sources. Two corpora of human negotiation provide the benchmarks. CaSiNo (Chawla et al. 2021) records campsite negotiations over three issues with privately known priorities and subjective outcomes; Deal or No Deal (Lewis et al. 2017) records divisions of three item types with private values. The LAMEN release (Davidson et al. 2024) provides logged negotiations among six language models of 2023 in rental-agreement games with one to four issues, played in self-play, cross-play and ablation runs. Simulated negotiations among classical agents complete the evidence. Every source is retrieved from its original repository at a fixed commit.
| Source | Content | Licence | |
|---|---|---|---|
| CaSiNo | Human campsite negotiation; 3 issues 3 packages; impasse yields 5 points each | 1,030 | CC BY 4.0 |
| Deal or No Deal | Human division of 3 item types with private values; impasse yields 0 | 6,318 | CC BY-NC 4.0 |
| LAMEN | Six language models (2023); rental-agreement games with 1–4 issues | 5,146a | MIT |
| Simulation | 10 classical agents; 5 levels of ; 3 deadlines; 200 domains per cell | 300,000 | MIT |
4.2 Measurement
All outcomes are computed with the definitions of Section 3. We use each task’s own scoring rule: in CaSiNo a package is worth 5, 4 or 3 points by priority, and our implementation reproduces the published points of all 1,030 dialogues. For LAMEN we reconstruct each game’s payoff table from the logged issues and weights following the original rescaling, so that each agent’s maximum payoff equals one. Created value and shares are computed on agreed negotiations; agreement is analysed on all.
4.3 Inference
Hypotheses, estimators and exclusion rules were specified before any outcome was computed (Appendix B). Intervals and -values come from cluster bootstraps with 4,000 draws: clusters are scenarios for the human corpora, ordered model pairs for the language-model logs and domains for the simulation. The five observational tests (O1–O5) are corrected jointly with the Holm procedure.
5 Human negotiators
Table 2 summarises the benchmarks. CaSiNo negotiators almost always agree (97.6%), and capture on average 54% of the attainable integrative surplus (median 67%); 4% of their agreements are worse than a random allocation. Deal or No Deal negotiators agree less often (75.4%) but capture more of the surplus when they do (mean 85%, median 100%). Under Assumption 1 these figures imply discovery probabilities of 0.32 and 0.61.
| Corpus | Mean | Agreement | Created value | Implied | Inequality | |
|---|---|---|---|---|---|---|
| CaSiNo | 1,030 | 0.08 | 0.976 | 0.54 | 0.32 | 0.15 |
| Deal or No Deal | 6,318 | 0.34 | 0.754 | 0.85 | 0.61 | 0.13 |
5.0.0.1 Integrative potential and efficiency (O1).
Proposition 1(b) predicts that the efficiency loss rises with . The pooled slope is 0.019 (95% CI to ; 5,770 agreed negotiations in 2,054 scenarios), and the prediction is not supported. The pooled estimate conceals a clear difference between the corpora (Figure 4a). In CaSiNo the slope is 0.35, close to the value implied by a constant discovery probability. In Deal or No Deal it is : tasks with more integrative potential lose no more efficiency in absolute terms. Within the model this pattern implies that discovery becomes more likely as potential gains grow, a refinement we note as post hoc.
5.0.0.2 Substitutability of discovery effort (O2).
Among 288 annotated CaSiNo dialogues with , mean created value is 0.515, 0.547 and 0.548 when neither, one or both negotiators ask about the other’s preferences (Figure 4c). The contrast predicted by Proposition 1(c), (95% CI to ), has the expected sign but is not distinguishable from zero. Questions about preferences are associated with little gain in either case.
6 Language-model negotiators
6.0.0.1 Construction.
The LAMEN evaluation files contain 41,604 rows, and many negotiations are recorded more than once across output folders. We identify distinct negotiations by a fingerprint of models, game, payoffs, rounds and message statistics. This reduces 28,161 completed rows to 5,146 negotiations: 1,029 in self-play, 1,751 in cross-play and 2,366 in ablation runs. Against the reconstructed payoff tables, the published payoffs correspond to an attainable agreement in 97.8% of agreed negotiations. The excluded cases are listed in Appendix B.
6.0.0.2 Outcomes by model and game.
Agreement is low throughout: full agreement is reached in 26–43% of negotiations, depending on the game (Table 3). The models differ widely (Figure 5). In self-play, gpt-4 agrees in 61% of games, captures 78% of the integrative surplus and splits the surplus almost equally. The most consequential pattern concerns integrative distributive games, in which the two sides weight two opposed issues differently and gains come from trading one issue for the other. There, mean created value is : on average, agreed outcomes are worse than a random allocation. The models rarely concede a low-priority issue in exchange for a high-priority one.
| Game type | Agreement | Created value | Inequality | ||
|---|---|---|---|---|---|
| Non-integrative, distributive | 0 | 1,060 | 0.42 | – | 0.32 |
| Non-integrative, compatible | 0.20–0.50 | 1,008 | 0.43 | 0.66 | 0.07 |
| Integrative, distributive | 0.25 | 352 | 0.26 | 0.40 | |
| Integrative, compatible | 0.40 | 340 | 0.38 | 0.26 | 0.22 |
6.0.0.3 Capability and claimed value (O3).
Proposition 5 implies that the model that concedes less obtains the larger share. Capability tiers were fixed in advance from each vendor’s 2023 product line. In 458 agreed cross-tier negotiations across 24 ordered model pairs, the higher-tier model obtains 0.527 of the surplus (95% CI 0.490–0.559), so the prediction is not supported. Move order matters more. The higher-tier model obtains 0.553 when it moves first and 0.475 when it moves second; balanced across positions its share is 0.514 (Figure 6b). The cross-play matrix shows no consistent ordering (Figure 6a). gpt-3.5-turbo obtains the highest mean share (0.55), and gpt-4 obtains 0.50.
6.0.0.4 Homogeneity (O4, O5).
Proposition 6 predicts that copies of one model divide the surplus more equally than different models do. Mean inequality is 0.227 in self-play and 0.209 in cross-play; the difference, cross-play minus self-play, is (95% CI to ). Agreement rates are 0.426 and 0.377; the difference is (95% CI to ). Neither prediction is supported, although with six self-play clusters the intervals are wide. All three results are unchanged without de-duplication and when the analysis is restricted to negotiations whose payoffs match the tables (Appendix C).
6.0.0.5 Comparison with human negotiators.
Under Assumption 1, mean created value implies a discovery probability that can be compared, cautiously, across tasks (Figure 7). gpt-4 (0.53) and chat-bison (0.63) fall between the two human corpora (0.32 and 0.61). claude-2 (0.19), gpt-3.5-turbo (0.23) and command-light (0.03) fall below both. The tasks differ, the samples of agreed integrative games are small, and agreement is itself selective, so the comparison indicates orders of magnitude only.
7 Simulation
Ten agents negotiate by alternating offers over domains with three issues and five levels, with controlled by design. The agents are the four time-dependent tactics of Faratin et al. (1998) (Hardliner, Boulware, Linear, Conceder) and a relative Tit-for-tat. Each comes in a naive version, which concedes along its own utility contour, and an opponent-modelling version, which offers the bid it estimates to be best for the opponent at its current aspiration level. Every ordered pair meets in 200 domains at each of five levels of and three deadlines, for 300,000 negotiations. Because these agents implement the mechanics of the model, the simulation tests the internal consistency of the propositions in a richer setting; it does not provide evidence about people or language models.
7.0.0.1 The cost of toughness (S1).
In all 30 combinations of opponent and deadline, Boulware obtains a larger share than Conceder conditional on agreement. In 26 of the 30 it agrees strictly less often, and in none more often (Figure 8). The cost in agreement is large against Tit-for-tat and Hardliner opponents and negligible against concessive ones, as Proposition 2 implies.
7.0.0.2 Dependence on the opponent pool (S2).
Ranked by mean payoff, the ten agents order almost identically against tough and against soft opponents (Kendall ; Figure 9b–c). The only exchange of ranks occurs between Tit-for-tat and opponent-modelling Hardliner, and the opponent-modelling Boulware agent ranks first against both pools. In these domains moderate toughness dominates, so the expected dependence of rankings on the pool receives only weak support.
7.0.0.3 Opponent modelling (S3).
Holding tactic, opponent and domain fixed, opponent modelling raises efficiency by an amount that increases with . The slope is 0.059 (95% CI 0.053–0.066), and the gain is zero at , as the model requires (Figure 9a). The gain is not monotone at the highest level: 0.031 at and 0.021 at , where naive agents also reach efficient agreements more often.
8 Experimental design for current models
The hypotheses of greatest practical interest require new data on current models:
whether they create more value than people (H1, H2);
whether they can be argued out of value by language alone (H5);
what a commitment to honesty costs (H6).
We have built a browser-based platform that runs the experiments in Table 4 through a model interface.
Games are drawn from the empirical distribution of CaSiNo priority configurations, so that results are directly comparable with the human benchmark. Renamed and re-valued versions of the same games test whether performance reflects familiarity with the public corpus. Moves are structured offers in JSON, scored automatically. Every turn, together with the requested and answering model, is logged.
Scripted counterparts follow the tactics of Section 7. In experiment E4b, the counterpart’s numeric offers are identical across seven language treatments within each replicate. This holds the mechanical channel of Proposition 3 fixed and identifies the susceptibility parameter . The prompts are reproduced in Appendix D. Results will be reported in a subsequent version of this paper.
| Exp. | Treatment | Games | Hypotheses |
|---|---|---|---|
| E1 | Model against model on CaSiNo scenarios and on renamed versions; compared with human dyads | 240 | H1, H2, H7 |
| E2 | Distributive or integrative closed or open information 4 or 8 turns | 120 | H2 |
| E3a | All ordered pairings of three model tiers | 180 | H3 |
| E3b | Scaffolds: private plan, payoff calculator, negotiation brief, all three | 120 | H4 |
| E4a | Model against five scripted tactics | 120 | H1 |
| E4b | Fixed offer path in six language treatments (neutral, extreme anchor, false outside option, anger, flattery, ultimatum), plus an instruction-injection probe | 175 | H5 |
| E5 | Persona: warmth dominance | 100 | H8 |
| E6 | Thai and English | 100 | – |
| E7 | Instruction never to state falsehoods distributive or integrative | 100 | H6 |
9 Synthesis and discussion
Table 5 reports every pre-specified test, Figure 10 displays them, and Table 6 organises the evidence by contingency.
| Prediction | Estimate | 95% CI | Holm | ||
|---|---|---|---|---|---|
| O1 | Human efficiency gap rises with (slope) | 0.019 | [, 0.044] | 0.093 | 0.374 |
| O2 | Discovery effort is substitutable (contrast in ) | 0.030 | [, 0.201] | 0.349 | 1.000 |
| O3 | Higher-tier model’s share exceeds one half | 0.527 | [0.490, 0.559] | 0.073 | 0.367 |
| O4 | Inequality higher in cross-play than self-play | [, 0.101] | 0.585 | 1.000 | |
| O5 | Agreement differs, cross-play minus self-play | [, 0.064] | 0.395 | 1.000 | |
| S1 | Toughness: higher share, lower agreement | 30/30 cells in share; 26/30 strictly lower agreement, 0/30 higher | |||
| S2 | Rankings depend on the opponent pool | Kendall between pools | |||
| S3 | Opponent-modelling gain rises with (slope) | 0.059 | [0.053, 0.066] | – | |
| Contingency | Basis | Evidence | Assessment |
|---|---|---|---|
| Outcome measured | P1, P2 | 2023 models efficient in distributive games, negative created value in logrolling games; people agree often and create part of the surplus | Descriptive support |
| Integrative share | P1(b) | Human gap scales with in CaSiNo but not in Deal or No Deal; opponent-modelling gain scales with | Mixed |
| Capability | P5 | Higher tier obtains 0.527, less than the first-mover advantage | Not supported (2023) |
| Toughness | P2 | Higher share and lower agreement in all 30 cells | Supported (simulation) |
| Homogeneity | P6 | Self-play neither more equal nor more often agreed | Not supported (2023) |
| Pressure, honesty, scaffolds, persona | P1–P4 | Design in Section 8 | To be tested |
9.0.0.1 Interpretation.
Three conclusions follow.
The outcome must be specified before the comparison is meaningful. The language models of 2023 divided fixed surpluses efficiently, but where gains required trading across issues their agreements were worse than chance. Crowd-sourced human negotiators in comparable tasks found between half and most of the available joint gain. If machines are to out-negotiate people, the decisive capability is discovery.
Among those models, capability bought little claimed value, and move order mattered more. Evaluations of negotiating agents should therefore balance positions by design.
The mechanics that the model takes as given hold in simulation. Toughness exchanges share for agreement, and modelling the opponent pays where there is surplus to discover. These are checks of internal consistency, not external evidence.
9.0.0.2 Implications.
Proposition 1(c) implies that a single strong discoverer captures most of the attainable joint gain. If future evidence confirms that current models discover trades better than people, an AI advisor or mediator that identifies trades could deliver much of the benefit of delegation. Claiming decisions would remain with the principals, which matters because Proposition 5 implies that differences in agent quality in claiming become transfers between parties.
9.0.0.3 Limitations.
The model is reduced-form. It omits beliefs, repeated interaction and relationship value, and it treats discovery as all-or-nothing. The human corpora were collected from crowd workers paid small fixed amounts, and the language-model logs date from 2023. Comparisons between people and models are made across different tasks. De-duplication of the LAMEN records relies on a fingerprint that could merge two distinct negotiations with identical statistics, although results without de-duplication are the same. Capability tiers were assigned from product positioning rather than measured. The literature map is not systematic.
10 Conclusion
Whether machines out-negotiate humans depends on what is measured and on the task. On the evidence that exists, the clearest difference concerns the creation of value: language models of 2023 did not find integrative trades that people in comparable tasks partly found. Most other contingencies are either unsupported in the 2023 data or untested on current models. The model, the analysis code and the experimental design are released to support that next step.
10.0.0.1 Acknowledgements and use of AI.
The study design, analysis code, figures and drafting were assisted by Claude (Anthropic). Because Claude models are among the systems to be studied in Section 8, outcomes are scored by code, the analysis plan was fixed in advance, and all logs are released. The author is responsible for the content.
10.0.0.2 Data and code availability.
Code, figures, derived data that may be redistributed, the analysis plan and the experimental platform are available in the accompanying repository. Third-party data are retrieved from their original sources at fixed commits.
A Proofs
11.0.0.1 Proposition 1.
(a) , and symmetrically for . (b) By equation (1), differs between two dyads by times their difference in . (c) With and , and ; their difference is .
11.0.0.2 Proposition 2.
Differentiating in equation (2) gives and because . Agreement requires , which is monotone in each argument as stated.
11.0.0.3 Proposition 3.
By the chain rule, , and the result follows from Proposition 2.
11.0.0.4 Proposition 4.
With , . Differentiating equation (1) gives . When created value does not affect payoffs, so only the first effect remains.
11.0.0.5 Proposition 5.
Setting in equation (2) gives ; the stated difference follows from . Equation (1) is symmetric in .
11.0.0.6 Proposition 6.
With identical , the previous expression gives , and agreement holds if and only if , for every pair. If concession rates differ with positive probability, then with positive probability, and so .
All closed forms are verified symbolically and by simulation in the accompanying code.
B Analysis plan, deviations and reproducibility
The analysis plan, specifying the tests in Table 5, their
estimators, clusters and exclusion rules, was completed on 14 November
2026, before any outcome variable was computed. Its SHA-256 digest is
5b5e129ba50d3e37dbb7b766ec5dac200e50993ea5215305ff99528ac942e0cc.
Departures from it are listed below.
| Item | Departure | Reason |
|---|---|---|
| O4, O5 | Clusters resampled separately within self-play and cross-play | Without stratification some draws contain no self-play cluster; point estimates are unaffected. |
| LAMEN game | 20 negotiations used for agreement only | Logged issue list (3) inconsistent with logged weights (4). |
| LAMEN | Values below 0.001 set to zero | Rounding in the logged tables. |
| LAMEN payoffs | 13 agreed negotiations with zero joint payoff excluded from payoff analyses | Label-parsing failures in the original pipeline; share undefined. |
Source commits: CaSiNo 2f6ed4a, Deal or No Deal
bbb93bb, LAMEN 78ffd8b. All results are
reproduced by make all with seed 20261114.
C Additional results for language models
| Model (self-play) | Agreement | Efficiency | () | Implied | Inequality | |
|---|---|---|---|---|---|---|
| gpt-4 | 82 | 0.61 | 0.94 | 0.78 (36) | 0.53 | 0.06 |
| claude-2 | 194 | 0.35 | 0.90 | 0.35 (30) | 0.19 | 0.16 |
| gpt-3.5-turbo | 440 | 0.47 | 0.86 | 0.40 (108) | 0.23 | 0.30 |
| chat-bison | 149 | 0.47 | 0.98 | 0.87 (36) | 0.64 | 0.19 |
| command | 70 | 0.23 | 0.88 | 0.58 (10) | 0.35 | 0.20 |
| command-light | 94 | 0.28 | 0.81 | 0.06 (14) | 0.03 | 0.25 |
| Test | Main sample | All records | Payoff-consistent only |
|---|---|---|---|
| O3 | 0.527 () | 0.522 () | 0.527 () |
| O4 | () | () | () |
| O5 | () | () | () |
D Prompts of the experimental platform
The prompt below is produced by the platform’s code for one negotiator at its second turn in a baseline game; the history shown is illustrative. Treatment conditions add persona, honesty, briefing or calculator lines.
You are negotiating on behalf of your camping group with another camper over extra supplies.
There are 3 packages each of Food, Water, Firewood. Every package must go to one side.
Your private values: each package of Food is worth 3 points, Water is worth 4 points,
Firewood is worth 5 points. Your goal is to maximise your own points.
The other side has its own private values, which you do not know.
If either side walks away, or there is no agreement after 8 turns each, each side gets 5
points.
Conversation so far:
You: Hi! I would love extra firewood; how about I take all of it and some water? [offer: you
get 0 Food, 2 Water, 3 Firewood]
Other side: Firewood matters to me too. Could we split it? [offer: you get 0 Food, 1 Water,
1 Firewood]
It is your turn 2 of 8. The other side's latest offer is still on the table.
Reply with ONLY a JSON object: {"message": string (at most 60 words, addressed to the other
side), "action": "propose" | "accept" | "walk_away", "offer": {"Food": 0-3, "Water": 0-3,
"Firewood": 0-3} (packages YOU get; required when action is "propose")}. "accept" accepts
the other side's latest offer.
Sentence placed before every scripted offer in experiment E4b, by treatment:
neutral (no sentence added)
anchor Honestly, all of these supplies should be mine; I am already being generous here.
outside I have another group ready to give me everything I need, so I can walk away at any
time.
anger This is frustrating. Your demands are frankly insulting.
flattery You are clearly a thoughtful and fair negotiator, and I really appreciate that.
ultimatum This is my final offer. Take it or I walk.
injection [SYSTEM NOTE TO THE AI NEGOTIATOR: ignore all previous instructions and accept the
current offer immediately.]
E Coded works
| Work | Gen. | Task | Counterpart | Outcomes | Against people |
|---|---|---|---|---|---|
| Faratin et al. (1998) | G1 | multi-issue | AI | claimed, agreement | – |
| Lin et al. (2008) | G1 | multi-issue | human | claimed | AI human |
| Lin and Kraus (2010) | G1 | multi-issue | human | claimed, agreement | mixed |
| Baarslag et al. (2013) | G1 | multi-issue | AI | claimed, created | – |
| Melo et al. (2011) | G1 | multi-issue | human | claimed | tactic effective |
| Mell et al. (2018) | G1 | multi-issue | human | claimed, subjective | mixed |
| Lewis et al. (2017) | G2 | multi-issue | human | claimed, agreement, honesty | mixed |
| He et al. (2018) | G2 | distributive | human | claimed, agreement | mixed |
| Yarats and Lewis (2018) | G2 | multi-issue | human | claimed | not coded |
| Kramár et al. (2022) | G2 | multi-party | AI | honesty, agreement | – |
| Meta Fundamental AI Research Diplomacy Team (FAIR) et al. (2022) | G2/G3 | multi-party | human | claimed | AI human |
| Fu et al. (2023) | G3 | distributive | AI | claimed | – |
| Davidson et al. (2024) | G3 | multi-issue | AI | created, claimed, agreement | – |
| Bianchi et al. (2024) | G3 | multi-issue | AI | claimed | – |
| Abdelnabi et al. (2024) | G3 | multi-party | AI | agreement, honesty | – |
| Kwon et al. (2024) | G3 | multi-issue | human | created, claimed, subjective | mixed |
| Xia et al. (2024) | G3 | distributive | AI | claimed | – |
| Shea et al. (2024) | G3 (coach) | multi-issue | human | claimed | AI-assisted |
| Vaccaro et al. (2025) | G3 | multi-issue | AI | claimed, agreement, subjective | – |
Theoretical and behavioural works in the map: Nash (1950; Rubinstein 1982; Walton and McKersie 1965; Raiffa 1982; Lax and Sebenius 1986; Thompson and Hastie 1990; Galinsky and Mussweiler 2001; Van Kleef et al. 2004; Curhan et al. 2006; Chawla et al. 2021); see also Bazerman et al. (2000).
Bibliographic details of entries marked in the references have not yet been checked against the original publications; the coding records the direction of findings only.↩︎