Zayx Shawn | Searcharxiv

arXiv2026

Faithful, Not Corrective: Message-Format Effects in Multi-Hop Agent Relays Are Tier-Dependent

When LLM agents hand off information to one another, does the message format matter? Two literatures disagree: format-optimization work reports that structured messages cut cost without hurting accuracy, while format-restriction work finds that imposing structure degrades generation -- and neither measures what happens when a message traverses multiple hops, where copy fidelity, not one-shot generation, dominates. We introduce a controlled relay testbed: briefs of twelve programmatically generated atomic facts are re-encoded hop-by-hop in five formats (free NL, precision-instructed NL, JSON, triples, key-value) over six hops, scored by a fixed strong grader against programmatic ground truth, across two relay-capability tiers, a cognitive-load condition, and a paired-fork error injection. We find that message-format effects are tier-dependent. (i) Under faithful-relay instructions a strong relay is nearly lossless -- the documented "telephone-game" collapse does not occur -- and adding per-hop cognitive load leaves format-level fidelity unchanged (within +/-1.8 points) while raising generation cost by 24-53%. (ii) Under a weak (1.5B) relay the across-format spread of six-hop recall grows by a factor of 8.7 (from 2.3 to 20.5 points), driven by two opposing mechanisms -- an encoding toll paid by the rigid formats and drift resistance specific to the fixed-key JSON schema -- that flip the format ranking in transit. (iii) In a paired-fork injection, an injected wrong value, once present, persists to the final hop in 83-100% of chains in every format, closely matching each format's retention of the true value, with no detectable collateral damage to neighboring facts. Structure buys a faithful, error-localizing channel -- not an error-correcting code -- and format choice should follow the weakest relay in the pipeline.

cs.AI↗

arXiv2026

PACE: Anytime-Valid Acceptance Tests for Self-Evolving Agents

Self-evolving agents improve by repeatedly proposing changes to their own prompts, skills, or workflows and keeping those that score higher on a small held-out set. Almost all effort has gone into the proposer that generates candidates; we argue the weak point is the acceptor, the rule that decides whether to commit a change. Applied hundreds of times against the same noisy dev estimate, the ubiquitous "keep it if the score went up" rule is uncontrolled adaptive multiple testing: the agent effectively p-hacks itself, accumulating false commits that make it churn and drift rather than improve. We recast committing as a sequential hypothesis test and propose PACE (Paired Anytime-valid Commit Evaluation), a training-free, anytime-valid commit gate. Each candidate is compared to the incumbent on identical instances and committed only when a testing-by-betting e-process accumulates decisive evidence, stopping early to save evaluations and controlling each candidate's false-commit probability at a user-set level even under optional stopping (a per-decision guarantee). On Qwen2.5 agents (0.5B-3B) self-evolving at the prompt level on GSM8K, SVAMP, and ARC-Challenge, greedy acceptance commits 30-42% false and 10-33% harmful edits when a genuine improvement is hidden among noisy proposals, while PACE commits the real one and essentially nothing else, matching greedy's held-out accuracy at sharply lower variance and about 18% lower evaluation cost. With no real gain available, greedy commits 13-21 spurious self-modifications per run (72-100% false) and degrades the most fragile agent by 4.9 points, while PACE holds at baseline. Reliability of self-evolution depends on the acceptor, not only on the proposer.

cs.AI↗