Belief-Calibrated Optimization: An Explicit World Model for Agentic Optimization

• URL: http://arxiv.org/abs/2609.01861v1
• Date: Tue, 01 Sep 2026 20:47:04 GMT
• Title: Belief-Calibrated Optimization: An Explicit World Model for Agentic Optimization
• Abstract summary: We introduce Belief-Calibrated Optimization (BCO), a method that writes that belief down as a persistent in-context document.<n>A fresh predictor given the accumulated document forecasts how the environment will respond more accurately than given either no document or a same-form copy whose content has been falsified.
• Score: 31.31831511580543
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The performance of an LLM agent depends on the scaffold around a frozen model. A common way to improve that scaffold is to use a coding agent as an optimizer: it reads current scores and traces and iteratively edits the source, producing a new candidate each round. Each edit is chosen according to a belief about how the environment will respond: what went wrong, and which change should help. That belief is typically implicit. It lives in the coding agent's reasoning on the current call, or remains latent in its parameters, rather than as something written down. Later calls therefore see scores and traces, but they do not use that belief. We introduce Belief-Calibrated Optimization (BCO), a method that writes that belief down as a persistent in-context document and continually revises that document as new candidates are evaluated. The resulting document is a world model: the current account of how the environment responds to edits. Added to an otherwise standard loop, BCO reaches a higher train passrate than a matched control that lacks only the world model, on five benchmarks spanning memory QA, tool-use QA, code-as-action app agents, and terminal agents. The gap remains on every held-out split, which is not used to select the candidate. After a target-model swap, in which the frozen model is replaced and the scaffold is not, the selected BCO scaffold leads on the tasks we test, except where context-window overruns leave it unfinished. An offline ablation then asks whether that gap comes from what the world model says. A fresh predictor given the accumulated document forecasts how the environment will respond more accurately than predictors given either no document or a same-form copy whose content has been falsified. The comparison indicates that the document carries reusable information in its content, not only in its form.

Related papers

• Assurance Envelopes for Autonomous Coding Agents: Minimum-Cost Evidence for Software Change [0.0]
  We ask which least-cost subset of available evidence re-establishes a required property.<n>We validate every selection by that closure rather than by trusting the closure.<n>Small graphs from Rust, IronBlocks, and Pong outcomes show that the minimum envelope depends on the task.
  arXiv  Detail & Related papers  (2026-09-14T20:06:46Z)
• Don't Let the Model Write the YAML: Deterministic, Minimal-Diff GitOps Remediation from LLM-Proposed Field Changes [0.0]
  In GitOps, having the model author the edited file or a diff is what practitioners reach for first.<n>We present an alternative that separates the semantic decision (which resource, field, and value) from the syntactic act of editing the file.<n>Because the file is never re-serialized, the diff is minimal by construction, and the edit is correct and deterministic independent of the model.
  arXiv  Detail & Related papers  (2026-08-31T18:37:12Z)
• The Working Set of a Coding Agent: Coherence Debt in Repository-Scale Tasks [14.070053515623883]
  Repository-scale coding requires an agent to keep tests, imports, configuration, and migration rules consistent within a bounded context window.<n>We supply and withhold each channel and inject faults across seven models and five harnesses.<n>When a rename defeats what models memorized about a real library, all seven fail in the same place, passing and missing the same tests.
  arXiv  Detail & Related papers  (2026-08-17T14:30:41Z)
• Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction [57.138342889101345]
  Tencent WorkBuddy Bench is a multi-domain evaluation suite for coding agents.<n>This report documents its construction methodology, scoring protocol, and a cross-model leaderboard.
  arXiv  Detail & Related papers  (2026-07-23T04:34:06Z)
• Contrastive Reflection for Iterative Prompt Optimization [0.6533652962118279]
  We present Contrastive Reflection, an iterative prompt-optimization framework for agentic IR.<n>We instantiate the framework with a tree-based slice selector, but the contribution is the contrastive loop rather than the tree itself.
  arXiv  Detail & Related papers  (2026-06-29T19:16:07Z)
• Bayesian-Agent: Posterior-Guided Skill Evolution for LLM Agent Harnesses [30.457068495035386]
  textbfBayesianAgent treats reusable skills and SOPs as hypotheses about whether a frozen model will succeed under a particular prompt, context, and harness environment.<n>Bayesian-Agent records verified trajectory evidence, maintains a feature-conditioned categorical posterior over each skill, and maps posterior state into inspectable actions such as patch, split, compress, retire, and explore.
  arXiv  Detail & Related papers  (2026-06-06T21:40:19Z)
• Lost in Decoding? Reproducing and Stress-Testing the Look-Ahead Prior in Generative Retrieval [48.348257016776195]
  Generative retrieval (GR) ranks documents by autoregressively generating document identifiers.<n>Many GR methods rely on trie-latency beam search, they are vulnerable to early pruning of relevant prefixes under finite-beam decoding.<n>Planning Ahead in Generative Retrieval (PAG) mitigates this failure mode by using simultaneous decoding to compute a document-level look-ahead prior that guides subsequent sequential decoding.
  arXiv  Detail & Related papers  (2026-04-25T17:58:15Z)
• ClawArena: Benchmarking AI Agents in Evolving Information Environments [61.664633997138004]
  ClawArena is a benchmark for evaluating AI agents in evolving information environments.<n>Each scenario maintains a complete hidden ground truth while exposing the agent only to noisy, partial, and sometimes contradictory traces.<n> evaluation is organized around three coupled challenges: multi-source conflict reasoning, dynamic belief revision, and implicit personalization.
  arXiv  Detail & Related papers  (2026-04-05T17:55:23Z)
• Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling [83.78874399606379]
  We propose MACT, a Multi-Agent Collaboration framework with Test-Time scaling.<n>It comprises four distinct small-scale agents, with clearly defined roles and effective collaboration.<n>It shows superior performance with a smaller parameter scale without sacrificing the ability of general and mathematical tasks.
  arXiv  Detail & Related papers  (2025-08-05T12:52:09Z)
• Language Modeling with Editable External Knowledge [90.7714362827356]
  This paper introduces ERASE, which improves model behavior when new documents are acquired. It incrementally deletes or rewriting other entries in the knowledge base each time a document is added. It improves accuracy relative to conventional retrieval-augmented generation by 7-13% (Mixtral-8x7B) and 6-10% (Llama-3-8B) absolute.
  arXiv  Detail & Related papers  (2024-06-17T17:59:35Z)
• DSI++: Updating Transformer Memory with New Documents [95.70264288158766]
  We introduce DSI++, a continual learning challenge for DSI to incrementally index new documents. We show that continual indexing of new documents leads to considerable forgetting of previously indexed documents. We introduce a generative memory to sample pseudo-queries for documents and supplement them during continual indexing to prevent forgetting for the retrieval task.
  arXiv  Detail & Related papers  (2022-12-19T18:59:34Z)

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.