Solver-in-the-Loop: MDP-Based Benchmarks for Self-Correction and Behavioral Rationality in Operations Research

Solver-in-the-Loop: MDP-Based Benchmarks for Self-Correction and Behavioral Rationality in Operations Research | Signal Canvas | ScienceToStartup

Page Freshness

Signal Canvas proof surface

Canonical route: /signal-canvas/solver-in-the-loop-mdp-based-benchmarks-for-self-correction-and-behavioral-rationality-in-operations-research

degraded

Proof freshness: stale
Proof status: failed
Display score: 9/10
Last proof check: 2026-03-19
Score updated: 2026-04-02
Score fresh until: 2026-05-02
References: 0
Source count: 0
Coverage: 33%

This page has proof data, but the latest verification did not complete cleanly.

Agent Handoff

Canonical ID solver-in-the-loop-mdp-based-benchmarks-for-self-correction-and-behavioral-rationality-in-operations-research | Route /signal-canvas/solver-in-the-loop-mdp-based-benchmarks-for-self-correction-and-behavioral-rationality-in-operations-research

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/signal-canvas/solver-in-the-loop-mdp-based-benchmarks-for-self-correction-and-behavioral-rationality-in-operations-research

MCP example

{
  "tool": "search_signal_canvas",
  "arguments": {
    "mode": "paper",
    "paper_ref": "solver-in-the-loop-mdp-based-benchmarks-for-self-correction-and-behavioral-rationality-in-operations-research",
    "query_text": "Summarize Solver-in-the-Loop: MDP-Based Benchmarks for Self-Correction and Behavioral Rationality in Operations Research"
  }
}

source_context

{
  "surface": "signal_canvas",
  "mode": "paper",
  "query": "Solver-in-the-Loop: MDP-Based Benchmarks for Self-Correction and Behavioral Rationality in Operations Research",
  "normalized_query": "2601.21008",
  "route": "/signal-canvas/solver-in-the-loop-mdp-based-benchmarks-for-self-correction-and-behavioral-rationality-in-operations-research",
  "paper_ref": "solver-in-the-loop-mdp-based-benchmarks-for-self-correction-and-behavioral-rationality-in-operations-research",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Evidence Receipt

Route status: degraded

Claims: 12

References: Pending verification

Proof: Verification pending

Freshness state: stale

Source paper: Solver-in-the-Loop: MDP-Based Benchmarks for Self-Correction and Behavioral Rationality in Operations Research

PDF: https://arxiv.org/pdf/2601.21008v1

Source count: Pending verification

Coverage: 33%

Last proof check: 2026-03-19T21:31:49.672Z

Signal Canvas receipt window

Watch and verify: Solver-in-the-Loop: MDP-Based Benchmarks for Self-Correction and Behavioral Rationality in Operations Research

/buildability/solver-in-the-loop-mdp-based-benchmarks-for-self-correction-and-behavioral-rationality-in-operations-research

Watchwatch

Subject: Solver-in-the-Loop: MDP-Based Benchmarks for Self-Correction and Behavioral Rationality in Operations Research

Verdict

Watch

Preparing verified analysis

GitHub Code Pulse

No public code linked for this paper yet.

Claim map

Strong 12Mixed 0Weak 0

Evidencepartial
Yet existing LLM benchmarks evaluate OR as one-shot translation -- given a problem description, generate solver code -- ignoring this diagnostic loop entirely.
Implicationmissing
Implication not extracted yet.
Verificationpartial
partial
Evidencepartial
\textbf{\ORDebug{}} evaluates iterative self-correction through 5,000+ problems spanning 9 error types; each repair action triggers solver re-execution and \IIS{} recomputation, providing deterministic, verifiable feedback.
Implicationmissing
Implication not extracted yet.
Verificationpartial
partial
Evidencepartial
\textbf{\ORBias{}} evaluates behavioral rationality through 2,000 newsvendor instances (1,000 ID + 1,000 OOD), measuring systematic deviations from closed-form optimal policies.
Implicationmissing
Implication not extracted yet.
Verificationpartial
partial
Evidencepartial
Across 26 models and 12,000+ samples, we find that domain-specific RLVR training enables an 8B model to surpass frontier APIs: 95.3\% vs 86.2\% recovery rate (+9.1\%), 62.4\% vs 47.8\% diagnostic accuracy (+14.6\%), and 2.25 vs 3.78 steps to resolution (1.7$\times$ faster).
Implicationmissing
Implication not extracted yet.
Verificationpartial
partial
Evidencepartial
On \ORBias{}, curriculum training achieves the only negative ID$\rightarrow$OOD bias drift among models evaluated (-9.6\%), reducing systematic bias by 48\% (from 20.0\% to 10.4\%).
Implicationmissing
Implication not extracted yet.
Verificationpartial
partial
Evidencepartial
These results demonstrate that process-level evaluation with verifiable oracles enables targeted training that outperforms scale.
Implicationmissing
Implication not extracted yet.
Verificationpartial
partial
Evidencepartial
We introduce two benchmarks that place the \textbf{solver in the evaluation loop}.
Implicationmissing
Implication not extracted yet.
Verificationpartial
partial
Evidencepartial
62.4% vs 47.8% diagnostic accuracy (+14.6%)
Implicationpartial
Directly stated in the abstract with explicit percentages.
Verificationpartial
partial
Evidencepartial
We introduce two benchmarks that place the solver in the evaluation loop. ORDebug evaluates iterative self-correction through 5,000+ problems spanning 9 error types
Implicationpartial
Directly stated in the abstract with specific numbers.
Verificationpartial
partial
Evidencepartial
domain-specific RLVR training enables an 8B model to surpass frontier APIs: 95.3% vs 86.2% recovery rate (+9.1%)
Implicationpartial
Directly stated in the abstract with explicit percentages.
Verificationpartial
partial
Evidencepartial
On ORBias, curriculum training achieves the only negative ID→OOD bias drift among models evaluated (-9.6%), reducing systematic bias by 48% (from 20.0% to 10.4%)
Implicationpartial
Directly stated in the abstract with specific numbers.
Verificationpartial
partial
Evidencepartial
Yet existing LLM benchmarks evaluate OR as one-shot translation — given a problem description, generate solver code — ignoring this diagnostic loop entirely.
Implicationpartial
Directly stated in the abstract as a limitation of prior work.
Verificationpartial
partial

Author intelligence and commercialization panels stay hidden until the proof receipt is verified, cites at least 3 references, includes at least 2 sources, and clears 50% coverage. The paper narrative and citation surfaces remain public while verification is pending.

Solver-in-the-Loop: MDP-Based Benchmarks for Self-Correction and Behavioral Rationality in Operations Research

Use Signal Canvas as the narrative proof surface

Use this Signal Canvas via API or MCP

Signal Canvas proof surface