Pith Number

pith:DDI4OEIX

pith:2026:DDI4OEIXPI7Y2SG3WSQ6CL2URP

not attested not anchored not stored refs resolved

TERMS-Bench: Diagnosing LLM Negotiation Agents Beyond Deal Rate

Aneesh Pappu, Batu El, Erica Zhang, Fangzhao Zhang, James Zou, Jiashuo Liu, Jose Blanchet, Susan Athey

A Bayesian-game testbed diagnoses LLM agents in price negotiation by measuring surplus extraction, cue use, and belief calibration rather than deal rate alone.

arxiv:2605.13909 v1 · 2026-05-13 · cs.GT · cs.AI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{DDI4OEIXPI7Y2SG3WSQ6CL2URP}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Evaluating 13 LLM agents spanning frontier systems, Terms-Bench shows frontier models saturate deal rate yet diverge in surplus extraction, cue use, belief calibration, and compliance, revealing agent-specific bargaining bottlenecks masked by prior benchmarks.

C2weakest assumption

The simulator policy and payoff structure chosen for the bilateral price negotiation accurately capture the strategic and informational features that matter in real human negotiations, so that observed gaps can be attributed to the agent rather than to an unrealistic environment.

C3one line summary

Terms-Bench is a diagnostic benchmark for LLM negotiation agents that reveals agent-specific strategic failures beyond simple deal rates by using hidden-type simulators as oracles.

References

57 extracted · 57 resolved · 0 Pith anchors

[1] The agent choosesAccept; the outcome is the counterpart’s last offered price

[2] The agent choosesReject; the outcome is disagreement⊥

[3] The counterpart accepts the agent’s offer; the outcome is the agent’s proposed price

[4] The counterpart terminally rejects (walk-away); the outcome is disagreement⊥

[5] The round limitKis reached without agreement; the outcome is disagreement⊥. Constraints.All Offer actions must satisfy: (i) price bounds pmin ≤p k ≤p max; (ii) monotonic concession: for buyer agents, 2025

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:18.840890Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

18d1c711177a3f8d48dbb4a1e12f548bc0efe1a77db62b56eabf834c869b52c9

Aliases

arxiv: 2605.13909 · arxiv_version: 2605.13909v1 · doi: 10.48550/arxiv.2605.13909 · pith_short_12: DDI4OEIXPI7Y · pith_short_16: DDI4OEIXPI7Y2SG3 · pith_short_8: DDI4OEIX

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/DDI4OEIXPI7Y2SG3WSQ6CL2URP \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 18d1c711177a3f8d48dbb4a1e12f548bc0efe1a77db62b56eabf834c869b52c9

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "cf73b9f7a06c72b9592ace0545de9a6a6dc3c1d6ed96695ce3e8caa82db7e40a",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.GT",
    "submitted_at": "2026-05-13T06:22:50Z",
    "title_canon_sha256": "89383b75c682bf5dd51e91c235c8d967cdbabfae06b7a96beb8335f37b90112b"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13909",
    "kind": "arxiv",
    "version": 1
  }
}