Wrong but Useful: Trajectory Value Beyond Answer Correctness in Multi-Agent Messages

• URL: http://arxiv.org/abs/2608.14375v1
• Date: Fri, 14 Aug 2026 15:16:57 GMT
• Title: Wrong but Useful: Trajectory Value Beyond Answer Correctness in Multi-Agent Messages
• Abstract summary: Multi-agent reasoning systems often use agreement, confidence, or automated scores to decide which messages should shape a final answer.<n>Yet a wrong answer can contain a useful decomposition, constraint, or scientific principle.<n>We test this distinction with Diverse Hypothesis Deliberation (DHD), a controlled measurement protocol that caches five independently generated messages.
• Score: 44.340269814027174
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-agent reasoning systems often use agreement, confidence, or automated scores to decide which messages should shape a final answer. Such filtering assumes that a message likely to be correct is also worth keeping. Yet a wrong answer can contain a useful decomposition, constraint, or scientific principle. We test this distinction with Diverse Hypothesis Deliberation (DHD), a controlled measurement protocol that caches five independently generated messages and replays the same downstream solver, called the integrator, with each message available or hidden. The replay comparison measures a message's trajectory value: whether making the message available helps or harms subsequent reasoning. Across five mathematics and science benchmarks and two openly available model families, gpt-oss-120b and gemma-4-31B-it, wrong-helpful messages appear in every benchmark-model combination. Among wrong-answer messages that change final correctness, more than four in ten changes are helpful in each model. Controlled repeats show that the number of repeatable message effects is unlikely to arise from replay variation alone (p=0.0002). A focused intervention on repeatable wrong-helpful messages finds that the complete message works best, while retaining its reasoning preserves more success than retaining only its answer; the source of the complete-message advantage remains open. Within the same problem, repeated trajectory-value evidence also identifies a better keep-or-remove choice than answer correctness alone. Answer correctness is therefore informative but does not determine trajectory value. DHD measures this missing property and produces reusable labels for learning when agents should listen.

Related papers

• Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong [1.2744523252873352]
  Black-box (behavioral) detection of unfaithful CoT against FaithCoT-Bench's human annotations.<n>We find answer correctness structures the problem at every level.
  arXiv  Detail & Related papers  (2026-07-26T04:43:53Z)
• Fantastic Adaptive Taxonomies and How to Use Them [100.20614173157708]
  AdaMAST converts execution traces into a compact, evidence-grounded failure taxonomy.<n>No code is hand-authored, no trace human-annotated.<n>In agent-system search, taxonomy-coded diagnoses of failed candidates outperform free-form.
  arXiv  Detail & Related papers  (2026-07-17T17:41:16Z)
• Does Verbose Chain-of-Thought Really Help? In-Distribution Evidence that Content, Not Length, Matters [10.230437172157474]
  Chain-of-thought prompting improves LLM reasoning, but the source is contested.<n>We repeatedly sample each model on the same question and pair a shorter with a longer of its own natural generations that follow the same reasoning plan.<n>We find that the extra tokens leave accuracy essentially unchanged for every independently-trained reasoner.<n>We ask whether two traces expressing the same semantic content produce different outcomes when one is more verbose.
  arXiv  Detail & Related papers  (2026-06-29T11:06:46Z)
• Trust but Verify: Prover-Verifier Deliberation for Selective LLM Prediction [4.273094752480624]
  We introduce prover-verifier deliberation (PVD), an inference-time protocol grounded in interactive proof theory.<n>PVD produces both an answer and a structured confidence verdict, allowing a system to report high-confidence answers while abstaining on uncertain cases.
  arXiv  Detail & Related papers  (2026-05-24T15:23:27Z)
• Reliable Chain-of-Thought via Prefix Consistency [6.053609157192373]
  We observe that traces with correct answers reproduce their original answer more often than traces with wrong answers.<n>We use this difference as a reliability signal, prefix consistency, that weights each candidate answer by how often it reappears under regeneration.
  arXiv  Detail & Related papers  (2026-05-08T12:28:05Z)
• QuantileMark: A Message-Symmetric Multi-bit Watermark for LLMs [43.011999511057134]
  QuantileMark is a white-box watermark that embeds messages within a cumulative probability interval.<n>It partitions this interval into $M$ equal-mass bins and samples strictly from the bin assigned to the target symbol.<n>For detection, the verifier reconstructs the same partition under teacher forcing, computes posteriors over latent bins, and aggregates evidence for verification.
  arXiv  Detail & Related papers  (2026-04-15T12:22:40Z)
• Pando: Do Interpretability Methods Work When Models Won't Explain Themselves? [53.07826484214082]
  We introduce Pando, a model-organism benchmark that breaks this confound via an explanation axis.<n>Pando predicts held-out model decisions from $10$ labeled query-response pairs.<n>When explanations are faithful, black-box elicitation matches or exceeds all white-box methods.
  arXiv  Detail & Related papers  (2026-04-13T06:42:24Z)
• Gaming the Answer Matcher: Examining the Impact of Text Manipulation on Automated Judgment [6.104512852467398]
  Automated answer matching shows substantial promise as a scalable and aligned alternative to human evaluation.<n>We investigate whether such tactics deceive answer matching models by prompting examinee models to generate verbose responses.<n>Our results show that these manipulations do not increase scores and often reduce them.
  arXiv  Detail & Related papers  (2025-12-22T17:39:13Z)
• High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned Finetuning [84.52940628494879]
  Large Language Models (LLMs) currently respond to every prompt.<n>LLMs can produce incorrect answers when they lack knowledge or capability.<n>We propose post-training an LLM to generate content only when confident in its correctness and to otherwise abstain.
  arXiv  Detail & Related papers  (2025-06-04T15:16:21Z)
• Latent Veracity Inference for Identifying Errors in Stepwise Reasoning [78.29317733206643]
  We introduce Veracity Search (VS), a discrete search algorithm over veracity assignments.<n>It performs otherwise intractable inference in the posterior distribution over latent veracity values.<n>It generalizes VS, enabling accurate zero-shot veracity inference in novel contexts.
  arXiv  Detail & Related papers  (2025-05-17T04:16:36Z)
• Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think [51.0691253204425]
  We analyze intermediate reasoning steps, termed subthoughts, to answer two questions: Does the final answer reliably represent the model's optimal conclusion?<n>Our approach involves segmenting a reasoning trace into sequential subthoughts based on linguistic cues.<n>We find that aggregating these answers by selecting the most frequent one (the mode) often yields significantly higher accuracy compared to relying solely on the answer derived from the original complete trace.
  arXiv  Detail & Related papers  (2025-04-29T12:39:07Z)
• AutoReply: Detecting Nonsense in Dialogue Introspectively with Discriminative Replies [71.62832112141913]
  We show that dialogue models can detect errors in their own messages introspectively, by calculating the likelihood of replies that are indicative of poor messages. We first show that hand-crafted replies can be effective for the task of detecting nonsense in applications as complex as Diplomacy. We find that AutoReply-generated replies outperform handcrafted replies and perform on par with carefully fine-tuned large supervised models.
  arXiv  Detail & Related papers  (2022-11-22T22:31:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.