A Framework for Argumentation-Based Agent \nNegotiation in Uncertain Settings
Bibliographic record
Abstract
Automated negotiation technologies are being increasingly used in business applications, especially in the e-Commerce domain. Argumentation-Based Negotiation (ABN), among the existing approaches, has been distinguished as a powerful approach to automated negotiation due to its ability to provide more sophisticated information (arguments) that justifies and supports agents’ proposals in order to mutually influence their preference relations on the set of offers, and consequently on the negotiation outcome. During the recent years, argumentation-based negotiation has received a considerable attention in the area of agent communication. However, current proposals are mostly concerned with presenting protocols for showing how agents can interact with each other, and how arguments and offers can be generated, evaluated and exchanged under the assumption of certainty. Therefore, none of these proposals is directly targeting the agents’ uncertainty about the selection of their moves nor designing the appropriate negotiation strategies based on this uncertainty in order to help the negotiating agents better make their decisions in the negotiation settings where agents have limited or uncertain information, precluding them from making optimal individual decisions. In this thesis, we tackle the aforementioned problems by advocating an Argumentation-Based Agent Negotiation (ABAN) framework that is capable of handling the problem of agents’ uncertainty during the negotiation process. \n We begin by proposing an argumentation framework enriched with a new element called agent’s uncertainty as an important parameter in the agent theory to allow negotiating agents to decide which moves to play and reason about the selection of these moves under the assumption of uncertainty. Then, a method for agents’ uncertainty assessment is presented. In particular, we use Shannon entropy to assess agent’s uncertainty about their moves at each dialogue step as well as for the whole dialogue. Negotiation strategies and agent profiles issues are also explored and a methodology for designing novel negotiation strategies and agent profiles under the assumption of uncertainty is developed. Moreover, two important outcome properties namely, completeness and Nash equilibrium are discussed. Finally, the applicability of our framework is explored through several scenarios of the well-known Buyer/Seller case study. The obtained empirical results confirm the effectiveness of using our uncertainty-aware techniques and demonstrate the usefulness of using such techniques in argumentation-based negotiations.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.010 | 0.009 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.004 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.003 | 0.008 |
| Scholarly communication | 0.009 | 0.008 |
| Open science | 0.006 | 0.007 |
| Research integrity | 0.006 | 0.006 |
| Insufficient payload (model declined to judge) | 0.006 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".