CP-Agent: A Calibrated Risk-Controlled Agent for Feedback-Driven Competitive Programming

• URL: http://arxiv.org/abs/2605.24693v1
• Date: Sat, 23 May 2026 18:13:41 GMT
• Title: CP-Agent: A Calibrated Risk-Controlled Agent for Feedback-Driven Competitive Programming
• Abstract summary: We model feedback-driven solving as a stopped process and identify three quantities: false-admission risk, program-level evidence against bad programs, and the active-state success hazard.<n>We instantiate mechanisms targeting these quantities as Dual-Granularity Verification, Test Augmentation, and Experience-Driven Self-Evolving, yielding CP-Agent.
• Score: 23.709197820809436
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models still struggle with contest-level programming, while many agentic remedies rely on massive inference-time sampling or expensive multi-stage post-training. We study when execution feedback reliably helps an LLM CP solver and which mechanisms govern the gains. We model feedback-driven solving as a calibrated stopped process and identify three quantities: false-admission risk, program-level evidence against bad programs, and the active-state success hazard. Under held-out trace calibration and selection from a pre-declared finite controller manifest, the resulting structural certificate lower-bounds the clean success probability before false admission. We instantiate mechanisms targeting these quantities as Dual-Granularity Verification, Test Augmentation, and Experience-Driven Self-Evolving, yielding CP-Agent. Without updating any parameters, CP-Agent raises Pass@1 from 25.8\% to 48.5\% on LiveCodeBench Pro and improves Refine@5 by 11.0\% on ICPC-Eval. Across three LLM backbones, CP-Agent lies on the cost--accuracy efficiency frontier, and ablations show that each component primarily affects its corresponding certificate quantity.

Related papers

• How to Speculate about Uncertainty in Agentic Coding? A Draft-Model Gate Method [4.37919186746582]
  We present Speculative Uncertainty (SU), a method that recovers a predictive failure signal for a black-box agent.<n>We extract phase-aware features by separating the reasoning and action spans, and calibrate them against a verifiable objective.<n>SU produces a failure-likelihood score that any downstream policy, such as routing, human intervention, or extra test-time compute, can consume directly.
  arXiv  Detail & Related papers  (2026-09-04T15:30:22Z)
• Knowing When to Ask for Help: Bayesian Self-Escalation in Hierarchical LLM Agents [0.0]
  Current agent systems decide delegation before reasoning begins.<n>We study a third regime: an agent that recognises, during its own reasoning, that it is unlikely to succeed.
  arXiv  Detail & Related papers  (2026-08-25T05:35:07Z)
• Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents [80.03824805228719]
  A major challenge in developing computer-use agents is collecting large-scale, high-quality trajectories.<n>We propose a data-centric paradigm that turns failed trajectories into agent improvements.<n>We validate this approach with the state-of-the-art OpenCUA-72B model on the OSWorld benchmark.
  arXiv  Detail & Related papers  (2026-06-30T07:44:37Z)
• MASPrism: Lightweight Failure Attribution for Multi-Agent Systems Using Prefill-Stage Signals [5.326315684098781]
  We propose MASPrism, a framework that performs failure attribution using prefill-stage signals from a small language model (SLM)<n> MASPrism processes each trace in 2.66 seconds on average, achieving a 6.69$times$ speedup over the single-pass prompting baseline, with zero output tokens.
  arXiv  Detail & Related papers  (2026-05-08T09:40:53Z)
• Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents [66.97968363332465]
  We introduce Claw-Eval, an end-to-end evaluation suite addressing all three gaps in agent benchmarks.<n>Claw-Eval comprises 300 human-verified tasks spanning 9 categories across three groups.<n>Every agent action is recorded through three independent evidence channels.
  arXiv  Detail & Related papers  (2026-04-07T17:43:18Z)
• LDP: An Identity-Aware Protocol for Multi-Agent LLM Systems [0.0]
  Current protocols do not expose model-level properties as first-class primitives, ignoring properties fundamental to effective delegation.<n>We present the LLM Delegate Protocol (LDP), an AI-native communication protocol introducing five mechanisms.<n>Identity-aware routing achieves 12x lower latency on easy tasks through delegate specialization, though it does not improve aggregate quality in our small delegate pool.
  arXiv  Detail & Related papers  (2026-03-09T19:13:17Z)
• Verified Critical Step Optimization for LLM Agents [67.05296684575445]
  Critical Step Optimization focuses preference learning on verified critical steps.<n>Method starts from failed policy trajectories rather than expert demonstrations.<n>Experiments on GAIA-Text-103 and XBench-DeepSearch show that CSO achieves 37% and 26% relative improvement over the SFT baseline.
  arXiv  Detail & Related papers  (2026-02-03T11:41:02Z)
• DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems [48.971606069204825]
  DoVer is an intervention-driven debug framework for large language model (LLM)-based multi-agent systems.<n>It augments hypothesis generation with active verification through targeted interventions.<n>DoVer flips 18-28% of failed trials into successes, achieves up to 16% milestone progress, and validates or refutes 30-60% of failure hypotheses.
  arXiv  Detail & Related papers  (2025-12-07T09:23:48Z)
• Alita-G: Self-Evolving Generative Agent for Agent Generation [54.49365835457433]
  We present ALITA-G, a framework that transforms a general-purpose agent into a domain expert.<n>In this framework, a generalist agent executes a curated suite of target-domain tasks.<n>It attains strong gains while reducing computation costs.
  arXiv  Detail & Related papers  (2025-10-27T17:59:14Z)
• Robust Uncertainty Quantification for Self-Evolving Large Language Models via Continual Domain Pretraining [7.344577590113121]
  Conformal Prediction (CP) has shown promise in offering correctness guarantees for large language models.<n>We introduce an adaptive rejection and non-exchangeable CP framework.<n>Our framework enhances both the effectiveness and reliability of CP under CDP scenarios.
  arXiv  Detail & Related papers  (2025-10-27T02:15:51Z)
• Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction [58.51530390018909]
  Large Language Model based multi-agent systems excel at collaborative problem solving but remain brittle to cascading errors.<n>We present MASC, a metacognitive framework that endows MAS with real-time, unsupervised, step-level error detection and self-correction.
  arXiv  Detail & Related papers  (2025-10-16T05:35:37Z)

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.