CatchBench: When Can an Agent Failure Be Caught?

• URL: http://arxiv.org/abs/2608.22808v2
• Date: Sun, 30 Aug 2026 19:25:12 GMT
• Title: CatchBench: When Can an Agent Failure Be Caught?
• Abstract summary: CatchBench puts one auditor's question to three information states.<n>Prior benchmarks fix one of these states or vary the telemetry.<n>Each state admits different questions, so seven task contracts carry their own labels and metrics.
• Score: 6.230697997280125
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: When can an agent failure be caught? An audit is usually limited by the record rather than by the method. CatchBench therefore puts one auditor's question to three information states: the declared configuration before a run (PRE), a growing prefix of its trace (LIVE), and the finished trace (POST). Prior benchmarks fix one of these states or vary the telemetry; to our knowledge none scores all three under one task-method interface. Each state admits different questions, so seven task contracts carry their own labels and metrics rather than one leaderboard. Four are evidential; three are Gold-derived mechanism diagnostics. The release scores 72 entrants, from rule scanners and structural models to eleven LLM judges across nine model families (GPT, Claude, Gemini, Gemma, Llama, Qwen, DeepSeek, Mistral, Nova), over 1187 declared configurations and 1162 recorded runs. Most of the arena does not order: 56 of 138 registered contrasts separate, and the rest are published unresolved rather than ranked. The two sharpest results cut against our own data. One rule ignores every name and permission; it flags each capability declared after the first. On one of six configuration sources it reaches a perfect F1, so a score there measures how the corpus was built rather than how well a method reasons. Our admissibility bar then rejected one injected substrate and withheld evidential status from the other. A benchmark number is therefore not interpretable until the process behind its labels is published and tested for the shortcut it may leave. We report both, and regenerate every ordering from released predictions with no model call.

Related papers

• NovaFabric: Tamper-Evident, Replayable Evidence for Autonomous AI Agent Runs [0.0]
  We present NovaFabric, producing audit-grade execution evidence.<n>It records an agent run, without modifying agent logic, into a portable Run Capsule.<n>Sealed runs are re-executable under a four-mode replay protocol.<n>We evaluate eight research questions at measured scope.
  arXiv  Detail & Related papers  (2026-09-11T08:35:43Z)
• IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier [0.0]
  All 18 audited benchmarks score advertised model identifiers.<n>A gold-blind capability-binding preflight verifies that a route can execute the evaluation contract before any task reaches it.<n>A reliability-inclusive first-pass scoring rule keeps failure in the score while keeping unsupported capability out.
  arXiv  Detail & Related papers  (2026-09-09T17:31:29Z)
• CAROL: Context-Aware Online Learning for Fuzzer Scheduling [30.06459480586687]
  Ensemble fuzzing runs multiple fuzzers on a target while a scheduler allocates CPU time among them.<n>We introduce CAROL, an online scheduler that uses each fuzzer's current context.<n>CAROL triggers more unique bugs than each of three ensemble-scheduling baselines whenever their results differ, and fewer on none.
  arXiv  Detail & Related papers  (2026-09-06T18:24:28Z)
• Clean Engineering, Unstable Measurement: A Preregistered Reliability Failure of Black-Box LLM Observers on Shared Endpoints [4.41537705949485]
  Language-model judges now gate training data, score generations, and drive leaderboards.<n>We audited that assumption in two preregistered campaigns with every threshold fixed in advance.<n>Across 52,988 audited request attempts, same-window repeat rankings agreed at Spearman 0.400 against a required 0.90.<n>We distill the evidence into a three-level snapshot-identity ladder, eight design rules, and a reporting checklist.
  arXiv  Detail & Related papers  (2026-09-03T17:59:43Z)
• VeriPhy: Agentic Physical Reasoning for World Model Evaluation and Refinement [57.86962208273888]
  We present an auditable physical-verification system in which a text-only planner compiles the prompt into typed physical obligations.<n>Each action returns a provenance-carrying evidence record whose payload, when usable, is either a typed measurement or an explicitly tagged learned state.<n>We anchor evaluation in a 1,500-clip corpus of human-annotated flaw records that localize real generation failures in prompt reference, space, and time.
  arXiv  Detail & Related papers  (2026-09-02T20:36:45Z)
• More Rejective, Not More Discriminative: The Unit of Verification in Pre-Execution LLM Oversight [3.8564927363194754]
  Pre-execution oversight is core to trusted monitoring in AI control.<n>Existing designs take the unit as given; its effect on fallible monitors is unmeasured.<n>Our framework is the first controlled, pre-registered instrument for this choice and never reads catch alone.
  arXiv  Detail & Related papers  (2026-08-25T00:59:55Z)
• K-Bench: measuring model performance on real scientific agent requests [0.0]
  K-Bench 01 is an evaluation built from first-turn requests sampled from live user traffic on K-Dense Web.<n>Three blinded language-model judges scored every run against an eight-dimension rubric.<n>Across all 39,934 scored judgments, 47.6% fall below the 8-point threshold.
  arXiv  Detail & Related papers  (2026-08-21T20:06:08Z)
• From Traceability to Justifiability: Accountability Structures in Agentic Software Engineering [0.0]
  We measure, from public material only, whether AI records can express a claim and whether they hold where declared.<n>Across 188 double-graded cells we found no platform whose default record emits a content identity of a behavioral system.<n>An instrument computes realized assurance depth from a pipeline's published exhaust alone and compares it with the declared depth.
  arXiv  Detail & Related papers  (2026-08-21T16:45:00Z)
• Quipu: A Governed Bitemporal Knowledge Graph Store [0.0]
  Quipu is an embeddable knowledge store that inverts four default defaults.<n>No fact enters except through a gate whose predicates evaluate the pending post-state.<n>A trace from a governed writer surfaces a live enforcement gap the audit names with its remediation.
  arXiv  Detail & Related papers  (2026-08-17T17:04:29Z)
• Harness-IF: Evaluating Instruction Following Across Instruction Surfaces in Coding Agents [29.96375986740068]
  Harness-IF scores operational rules one at a time from execution evidence.<n>AP-Acc scores only rules labeled as opposing unprompted defaults.
  arXiv  Detail & Related papers  (2026-08-12T07:07:57Z)
• The LLM Proposes, the Executive Disposes: A Self-Verifying Agent Instrument that Dissociates Commitment Drift from Binding Drift in Long-Horizon Agents [0.0]
  We present an agent instrument built so that verification is structural rather than post-hoc.<n>Every run invalidates itself when per-organ write-error, render-size, or salted-canary-echo floors are breached.<n>We report a clean, single-variable result on a failure every long-horizon agent suffers.
  arXiv  Detail & Related papers  (2026-08-04T15:10:37Z)
• CallScreenBench: Benchmarking On-Device Models as Phone Secretaries [3.917303377795418]
  A phone secretary takes an unknown inbound call on its owner's behalf.<n>Unlike the agents evaluated by most benchmarks, it has no task to complete and no cooperative user.<n>We present CallScreenBench, which scores this setting on five quality dimensions.
  arXiv  Detail & Related papers  (2026-08-02T06:31:25Z)
• Turning Interaction History into Execution State: A Runtime Layer for Long-Horizon Coding Agents [48.967927222079965]
  Ledger is a runtime layer that distills an agent's completed interactions into an explicit execution state.<n> Ledger keeps this state in an online execution ledger and applies it at two boundaries of every step.<n>Across all 500 SWE-bench Verified instances, Ledger raises Pass@1 from 56.2% to 64.2% with GPT-5 mini and from 75.8% to 81.0% with MiniMax M2.5.
  arXiv  Detail & Related papers  (2026-08-01T18:25:00Z)
• DarwinX: Evolving Agent Harnesses Through Natural Selection [48.64258219266629]
  DarwinX treats self-evolution as selection over a population of harnesses with the model frozen.<n>General agent competence, not benchmark-specific patches, so it survives changes of task, verifier, and base model.
  arXiv  Detail & Related papers  (2026-07-31T05:34:02Z)
• HALLMARK: Diagnosing Three Failure Modes in LLM Citation Verifiers [30.02579334273979]
  GPTZero found 53 papers with hallucinated citations among NeurIPS 2025's accepted set.<n>No shared benchmark compares verifiers and gives detailed failure diagnostics.<n>Hallucination benchmark: 2,526 Bib entries spanning 14 types, three difficulty tiers, six diagnostic sub-tests per entry.
  arXiv  Detail & Related papers  (2026-07-20T13:21:27Z)
• Abliteration Is Not a Scalpel: Off-Target Effects of Refusal Removal on Decision Disposition Across Model Families [51.56484100374058]
  Abliteration - deleting a model's refusal direction from its weights - is the standard recipe behind popular "uncensored" open-weight models.<n>As a disposition probe we use 21,600 decisions under uncertainty, replayed through a frozen pipeline so the decision-layer model is the only variable.<n>Three effects replicate across both families (weeks-clustered CIs excluding zero)<n>A fourth effect reverses sign: the same operation makes Gemma-abliterated less confident and Qwen-abliterated more (family CIs non-overlapping)
  arXiv  Detail & Related papers  (2026-07-19T22:27:00Z)
• AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents [34.450981549319266]
  Memory for a long-horizon LLM agent is a contract about what each future decision is allowed to see.<n>We instrument an alternative bounded contract: every decision is made from a fresh user message assembled by typed retrieval.<n>We instantiate the contract in Slay the Spire 2, a closed-rule deck-building game.
  arXiv  Detail & Related papers  (2026-07-02T14:44:32Z)
• CoEval: Ranking Language Models for Custom Tasks Without Labeled Data or Trustworthy Benchmarks [47.027290803102666]
  We present CoEval, an open framework that supplies a trustworthy, task-specific signal through ensemble self-evaluation.<n>A pool of models rotates through all three roles, teacher, student, and judge, to generate a fresh, contamination-free benchmark.
  arXiv  Detail & Related papers  (2026-06-02T13:41:43Z)
• Do Large Language Model Benchmarks Test Reliability? [66.1783478365998]
  We investigate how well current benchmarks quantify model reliability.<n>Motivated by this gap in the evaluation of reliability, we propose the concept of so-called platinum benchmarks.<n>We evaluate a wide range of models on these platinum benchmarks and find that, indeed, frontier LLMs still exhibit failures on simple tasks.
  arXiv  Detail & Related papers  (2025-02-05T18:58:19Z)

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.